{"as_of":"2026-08-16T08:22:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ecdd2ce2379e4d53a0e042935c3090c430914858dd6aa6ef36505248b974514c","coverage":[{"denominator":168,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":100,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T20:14:25.101829Z","state":"measured"},{"denominator":102,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":102,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-16T06:30:59.297886+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-08T17:56:09.884837Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-12T10:46:31.754330Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"cited_work":{"arxiv_id":"2411.09945","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2411.09945","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"TEESlice: Protecting sensitive neural network models in trusted execution environments when attackers have pre-trained models","venue":null,"work_id":"502d36db-8136-4fec-a18c-dfa5d3a25f15","year":2024},"citing_paper":{"arxiv_id":"2605.03213","last_updated":"2026-05-07T16:46:43Z","snapshot_observed_at":"2026-08-14T07:51:15.831884Z","submitted_at":"2026-05-04T23:09:16Z","title":"When Agents Handle Secrets: A Survey of Confidential Computing for Agentic AI","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-05-07T02:12:30.086152Z"},"links":{"cited_paper":"/paper/2411.09945","citing_paper":"/paper/2605.03213"},"observation_digest":"sha256:536f0c601bc82af6b151d81fba61874df7e7d02e95fba89c9623cb63d9aa4858","observation_id":"023da1d1-28ed-4a64-b2e3-b7d57a9b0d4c","resolution":{"observed_at":"2026-05-12T10:46:31.757375Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"cited_work":{"arxiv_id":"2411.09945","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2411.09945","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"TEESlice: Protecting sensitive neural network models in trusted execution environments when attackers have pre-trained models","venue":null,"work_id":"502d36db-8136-4fec-a18c-dfa5d3a25f15","year":2024},"citing_paper":{"arxiv_id":"2605.03213","last_updated":"2026-05-07T16:46:43Z","snapshot_observed_at":"2026-08-14T07:51:15.831884Z","submitted_at":"2026-05-04T23:09:16Z","title":"When Agents Handle Secrets: A Survey of Confidential Computing for Agentic AI","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-05-08T17:56:09.884837Z"},"links":{"cited_paper":"/paper/2411.09945","citing_paper":"/paper/2605.03213"},"observation_digest":"sha256:c2e09c25480ab89fd34d9131f0f7c7a2061052f796c02dab3191c991818379d6","observation_id":"87fee389-56d2-44f0-95d9-27fc7bd8b083","resolution":{"observed_at":"2026-05-09T06:55:45.470510Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2411.09945/citation-record","integrity":"/paper/2411.09945/integrity","json":"/paper/2411.09945/citation-record.json","paper":"/paper/2411.09945"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:24.668940Z","title":"Knockoff Nets Demo Code","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:24.668940Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:03c7bd6419b343759d77085fb8f7f7f5250d6fa9f05089bb187af65a1db43bb5","observation_id":"643f8c6e-fd56-42fc-9b24-07c09f37e176","resolution":{"observed_at":"2026-08-12T20:14:24.668940Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:24.673346Z","title":"ML-Doctor Demo Code","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:24.673346Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:f27e9296851720e556aaa73901919b1f395784ffa8c76ed210d5152b2fdbadef","observation_id":"3f7f9ba0-eed8-41f8-8422-6b3642ffb75c","resolution":{"observed_at":"2026-08-12T20:14:24.673346Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:24.677750Z","title":"One-time pad","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:24.677750Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:30070a4d93e3b240d4a97cb25f38906193ad5d493c01ffadba42a20ad5f51185","observation_id":"dd16bda5-cc4e-4b38-8277-b42355194de2","resolution":{"observed_at":"2026-08-12T20:14:24.677750Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:24.682073Z","title":"Android 7.0 Compatibility Definition","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:24.682073Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:09518cf1c5784de551a8bfa376493f7cac6ac9e85dc442f553d6d53da31f4f73","observation_id":"7d535393-30eb-42e7-8b5a-91c9984d64f5","resolution":{"observed_at":"2026-08-12T20:14:24.682073Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:24.686111Z","title":"Artifact","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:24.686111Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:141d528f5be14395c543b84125261566548fba5648ed497639dfba29b8155f6e","observation_id":"f89c8110-8574-4014-9197-634e2106465d","resolution":{"observed_at":"2026-08-12T20:14:24.686111Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:24.690071Z","title":"Full Supplementary","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:24.690071Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:b367f9367ce9e2c719d0e19518e5c738cb9ba3d0c57ee8d4a016278223319be6","observation_id":"86f76f0f-d50b-43df-8827-a7bb9fd450c0","resolution":{"observed_at":"2026-08-12T20:14:24.690071Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:24.694133Z","title":"OP-TEE documentation Raspberry Pi 3","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:24.694133Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:1849751a0897255b3c9b0199779b0433715410b1df7c84992b608b785d264402","observation_id":"f0af1495-0601-40ee-9b1b-90cda497101f","resolution":{"observed_at":"2026-08-12T20:14:24.694133Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:24.697956Z","title":"Artifact for LLM","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:24.697956Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:ce7ea8e88cc309fd336973673bae763997e102184ffcb99db1fa572207ce8569","observation_id":"2f0d6b9a-d261-48f2-8e86-946fbfa5aebf","resolution":{"observed_at":"2026-08-12T20:14:24.697956Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:24.702189Z","title":null,"venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:24.702189Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:b73f9d436146ed1db61d70d695a4cbdb628ed30f3d1c2e6aecc8854cc9143093","observation_id":"c44992c3-45b5-4c26-8efa-10053b8d8624","resolution":{"observed_at":"2026-08-12T20:14:24.702189Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:24.705810Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:24.705810Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:962ec5303e7b4c9a475ef0183200ef0e95a6185452ce0f71c157c2ce5bf2f9dc","observation_id":"b12ed0ed-43fd-4acc-a402-0279edb7d7ff","resolution":{"observed_at":"2026-08-12T20:14:24.705810Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:24.709574Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:24.709574Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:a7f6e0a37c1aead453a7cba308051789901fc224fffcef5d4040755614d18569","observation_id":"4fae174b-e775-495b-b453-237b3e0c304f","resolution":{"observed_at":"2026-08-12T20:14:24.709574Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:24.714166Z","title":null,"venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:24.714166Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:205b198f9c8fe983646be6823040e7693bc0a7b846147cb7c76c599c636aeb01","observation_id":"cc488c5f-1345-40cb-afbb-917bd4e9d8b8","resolution":{"observed_at":"2026-08-12T20:14:24.714166Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:24.718491Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:24.718491Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:9fd3028f14390db4ffa6946d14daa77adec5691948407aba9dde28b70f0d6f90","observation_id":"1f8bcc7a-a47f-457b-a245-f806802dece7","resolution":{"observed_at":"2026-08-12T20:14:24.718491Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:24.722325Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:24.722325Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:0e01dca5b27e2780db6c107020ad4b38bf236febfcefb6096b7d7834824da0ba","observation_id":"a2161b3b-23aa-4ea2-9be8-9f18c87072e9","resolution":{"observed_at":"2026-08-12T20:14:24.722325Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:24.725792Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:24.725792Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:edda63758e23f552a0dc0df7630b6929bdd0970e69eefd251133c9a6b3858b09","observation_id":"856f8e72-e3bf-47e7-ae7b-d9dd39b8ffac","resolution":{"observed_at":"2026-08-12T20:14:24.725792Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:24.729702Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:24.729702Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:5855295ede6e40e1507d3c3bd4abf5881180f1a601f04782c40e15959cab0cb8","observation_id":"96545283-6be7-439e-95e2-069aba818146","resolution":{"observed_at":"2026-08-12T20:14:24.729702Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:24.742597Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:24.742597Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:ab7039b34bc4068179e57be5de35f825fa4f18063268f7fa676099e6bc0bdf42","observation_id":"dcc6e380-e367-4988-9305-b3d60e4413f8","resolution":{"observed_at":"2026-08-12T20:14:24.742597Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:24.746419Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:24.746419Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:7c5915d7ea99bfbf7d2845f49c736a1b4ca09a694010dc0502208b7d5794a1cd","observation_id":"481bb3fd-6efc-48ba-8f59-aedb5849ff10","resolution":{"observed_at":"2026-08-12T20:14:24.746419Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2019.29630","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:28.398745Z","title":null,"venue":null,"work_id":"c18dbad9-4a75-4a83-942e-54e5c049d80f","year":2020},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:24.750285Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:3137915bd985533366c18c9b772b3bb563753149225d26f451ef1120fb1d4c27","observation_id":"3edb8cec-e2a6-48d0-bb15-1f186075a2aa","resolution":{"observed_at":"2026-08-12T20:14:28.405325Z","resolver_source":"raw_fallback","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:24.754094Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:24.754094Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:6a963049c47846294f75cadd1c361d1a893affb52f372270f794556edba37c25","observation_id":"f27ad94f-619c-406d-9f48-19f9500cdde7","resolution":{"observed_at":"2026-08-12T20:14:24.754094Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:24.757979Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:24.757979Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:b43181627e256f218c5e286cd3971cd6a49af81ea0fb85b212ecba80f66a8657","observation_id":"5de53a38-292c-4f11-8bc3-26a1878d7d68","resolution":{"observed_at":"2026-08-12T20:14:24.757979Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:24.766081Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:24.766081Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:365eed091a5a95189ad77051c4728cca114584c9a0f60db5c0c9ab2382cbdf57","observation_id":"4df8a29b-5e32-42cf-b368-bb201f219607","resolution":{"observed_at":"2026-08-12T20:14:24.766081Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:24.770410Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:24.770410Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:dc6b22dba78d6c8f9f56740f9be0ad33e94eacbc081caaa2751c7cb3ccfabbcf","observation_id":"f59f7827-3907-4fad-bc57-4a23c7b61343","resolution":{"observed_at":"2026-08-12T20:14:24.770410Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:24.774768Z","title":"Ng, and Honglak Lee","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:24.774768Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:f676487ac6e23a0416493bb98119cf6bc2bef1ec74049009cfbf6e70d813d828","observation_id":"c17396c0-e19f-4383-a35e-123b7649bbcb","resolution":{"observed_at":"2026-08-12T20:14:24.774768Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:24.779200Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:24.779200Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:50643c8f638d6bec7da8b9ec3307ec8393194c45295670dfcb45e894b3701ce9","observation_id":"a3e698a2-fd82-4342-8bc4-41543c31df8d","resolution":{"observed_at":"2026-08-12T20:14:24.779200Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:24.783626Z","title":null,"venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:24.783626Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:9cb7feb6a86141957f3482f14fbc730710e187fab06ededd8c44b9c102916e96","observation_id":"e96ed687-e805-492c-93ee-886693db1e5e","resolution":{"observed_at":"2026-08-12T20:14:24.783626Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2002.01535","last_updated":"2020-02-04T21:02:11Z","snapshot_observed_at":"2026-08-06T22:50:38.500329Z","submitted_at":"2020-02-04T21:02:11Z","title":"Lightweight Convolutional Representations for On-Device Natural Language Processing","version":1},"cited_work":{"arxiv_id":"2002.01535","doi":null,"metadata_source":"pith","pith_arxiv_id":"2002.01535","snapshot_observed_at":"2026-08-12T20:14:28.076591Z","title":"Lightweight Convolutional Representations for On-Device Natural Language Processing","venue":"cs.CL","work_id":"3d73e40e-9760-44f7-adc2-29fd6c5d0b3a","year":2020},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:24.788243Z"},"links":{"cited_paper":"/paper/2002.01535","citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:51b11958b3c691543210b2204dc39e45ea58678000192885df47665d23dabf46","observation_id":"f3e32d19-b154-4e06-8d23-daf6b7ef403d","resolution":{"observed_at":"2026-08-12T20:14:28.080938Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:24.793049Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:24.793049Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:2a9183707c6a2b3a4efafa70a4d1ef7519c04d1839fbdb7faeba97a0885bfe0f","observation_id":"130f49ad-de38-4a0f-b525-7d42ef90b7ee","resolution":{"observed_at":"2026-08-12T20:14:24.793049Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.11929","last_updated":"2021-06-03T13:08:56Z","snapshot_observed_at":"2026-08-13T14:19:26.598265Z","submitted_at":"2020-10-22T17:55:59Z","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.11929","snapshot_observed_at":"2026-08-12T20:14:24.797643Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:24.797643Z"},"links":{"cited_paper":"/paper/2010.11929","citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:c711257ecd91245491be9870e49cdb701006b43e76d739d668f4506f7af14b89","observation_id":"1e7a0664-5de4-47d6-9c83-104e17de5b7c","resolution":{"observed_at":"2026-08-12T20:14:24.797643Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2211.31344","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:28.046473Z","title":null,"venue":null,"work_id":"2facb6e2-00a0-49a5-8ffc-3c20e9511c24","year":2017},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:24.803028Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:f496cfbd004b597c17ed38941169bceb217486c6e296af83f8f06cb77a1eb939","observation_id":"d985ed68-6a46-46f6-9ee1-b3d3a12005d1","resolution":{"observed_at":"2026-08-12T20:14:28.051984Z","resolver_source":"raw_fallback","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:24.807564Z","title":null,"venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:24.807564Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:ad3ac587925f144a19ed1a5284a3a76fdd6aa5c6e6f4d589d228308f371593e4","observation_id":"0dcbf7d6-ed46-4ec3-9429-864e74e3bf90","resolution":{"observed_at":"2026-08-12T20:14:24.807564Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:24.811995Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:24.811995Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:81230ae2437fa541928ad1ee48356f35597350a455d2ab2e8ef1c044aabd79cb","observation_id":"78664bee-6f86-4786-8330-8d17e56ee497","resolution":{"observed_at":"2026-08-12T20:14:24.811995Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:24.816820Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:24.816820Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:c1d1829f42d858bb4010db8b1617edfb4e0b7689dc3bce0c4e6e975ae0b6af74","observation_id":"36a6b583-ba00-4d6e-8bda-cc5e0a15457b","resolution":{"observed_at":"2026-08-12T20:14:24.816820Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:24.821294Z","title":null,"venue":null,"work_id":null,"year":1977},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:24.821294Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:642f737ed0985d18aa9a9425c2fa636e3e70202e09838317cc10cbd9c656c162","observation_id":"9a96c959-7689-4c83-94a4-3cab0bc894fa","resolution":{"observed_at":"2026-08-12T20:14:24.821294Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:24.825571Z","title":"Lauter, Michael Naehrig, and John Wernsing","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:24.825571Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:2a7cef3d5a6f18f6d3535e84dbf045ecaf23774863504e994c087a3a1b36fa6b","observation_id":"af055236-2dfa-4b8d-9b01-3c3f86d99ef8","resolution":{"observed_at":"2026-08-12T20:14:24.825571Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:24.830504Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:24.830504Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:2c6853b26642d52a8b7c48c57d38dcc3c6e656405a1a6dafb0f0bb2ae8cd4192","observation_id":"16e2686c-7a21-4c10-9eb4-0984284a68bf","resolution":{"observed_at":"2026-08-12T20:14:24.830504Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:24.834094Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:24.834094Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:8b7e0777203fd6592432e252f71f16399b0c24ef97d882e4cacc46a306accbe9","observation_id":"8e6d014b-228d-43d1-83d9-e39cc0982033","resolution":{"observed_at":"2026-08-12T20:14:24.834094Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:24.838042Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:24.838042Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:fa54c556c9f4ab11304c22472bc81c016b8c3c493a585d87dd66c618c48a725e","observation_id":"9cea6395-6948-49bd-a5cd-89463ec30dab","resolution":{"observed_at":"2026-08-12T20:14:24.838042Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:24.841808Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:24.841808Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:024796abe091cbb62c1e853451803c35d3be930f820937a350152d5664d28438","observation_id":"0c9a995f-f2bd-40c3-bbd4-347a36acf812","resolution":{"observed_at":"2026-08-12T20:14:24.841808Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1807.00969","last_updated":"2020-08-12T20:36:53Z","snapshot_observed_at":"2026-08-14T18:56:23.118450Z","submitted_at":"2018-07-03T04:00:15Z","title":"Confidential Inference via Ternary Model Partitioning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1807.00969","snapshot_observed_at":"2026-08-12T20:14:24.845578Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:24.845578Z"},"links":{"cited_paper":"/paper/1807.00969","citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:20b752f41b9ba0280dee7c26e58f9424d39737106e8c0df14cf89bc41d593144","observation_id":"1e09350b-d344-4c4b-b480-f3ec6ed5d770","resolution":{"observed_at":"2026-08-12T20:14:24.845578Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:24.849721Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:24.849721Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:4f9d9f62259f846d5ed3004fc4401e1b1fa5cb53f851b7a775466d1b5e6296a1","observation_id":"be11c6b7-710e-48ab-b43c-9284da4387c5","resolution":{"observed_at":"2026-08-12T20:14:24.849721Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:24.857616Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:24.857616Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:ba8c43d424116b13e402054d12aa2202daf3bd6a5f42b8c04031bde1fe88065d","observation_id":"dddee61b-b8e5-4b39-a929-af0479b4147a","resolution":{"observed_at":"2026-08-12T20:14:24.857616Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:24.862114Z","title":null,"venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:24.862114Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:56803143ea350b5eaa9533c2c1b54066ce87dd29426d5241d3cb5128f4580dc3","observation_id":"aebd2840-6720-4a9e-8468-7f3b344727e6","resolution":{"observed_at":"2026-08-12T20:14:24.862114Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:24.869983Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:24.869983Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:4f80597d568e8e0057f1ffc01c9317eb54875fe29bf354d16b666bad7eec9bd0","observation_id":"754833bc-8c9e-4586-a6a6-c191ae778a2e","resolution":{"observed_at":"2026-08-12T20:14:24.869983Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:24.873955Z","title":"Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:24.873955Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:814289e74bcd4569ae9e842ee39a161112ff736f926a9ac4a1c3a5eed41759cc","observation_id":"8bb21246-4186-436f-99fb-4db158792bf1","resolution":{"observed_at":"2026-08-12T20:14:24.873955Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:24.881024Z","title":"Yu, and Xuyun Zhang","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:24.881024Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:2c0081d320c245705e4b6ec255380df2b13f93f40f559737d46a30b713ea4e58","observation_id":"6c41d576-1722-4f32-98a0-0a7a4966d5bc","resolution":{"observed_at":"2026-08-12T20:14:24.881024Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:24.884616Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:24.884616Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:977b851f370422683f2142288ec8b13fff85a7b2795f5993b9db8a48d4d6860e","observation_id":"30d81876-abc7-416c-8fa5-a1663615b9be","resolution":{"observed_at":"2026-08-12T20:14:24.884616Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:24.877647Z","title":"In The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25-29, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:24.877647Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:35dd8eb6be044e28cc27a844e0c74fec33e39ce6384895a21f120e46d0e6d8a2","observation_id":"6d25424d-4000-416c-b284-ccaf23f6dddd","resolution":{"observed_at":"2026-08-12T20:14:24.877647Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:24.892906Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:24.892906Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:8474525cd07a21f889a9881d966166797963d64132c9de92a58a492698fa4460","observation_id":"746e166b-c1ed-47ff-ad92-2be7cf827f08","resolution":{"observed_at":"2026-08-12T20:14:24.892906Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2008.11632","last_updated":"2022-05-25T17:59:34Z","snapshot_observed_at":"2026-07-06T09:50:22.512464Z","submitted_at":"2020-08-26T15:43:50Z","title":"GuardNN: Secure Accelerator Architecture for Privacy-Preserving Deep Learning","version":2},"cited_work":{"arxiv_id":"2008.11632","doi":null,"metadata_source":"pith","pith_arxiv_id":"2008.11632","snapshot_observed_at":"2026-08-12T20:14:27.648896Z","title":"GuardNN: Secure Accelerator Architecture for Privacy-Preserving Deep Learning","venue":"cs.CR","work_id":"6ddcaad1-7f21-40d8-88e8-c812f9a03879","year":2020},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:24.897240Z"},"links":{"cited_paper":"/paper/2008.11632","citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:fd6e755a711c468c5972564708abee815c5c2d44a2179358f412e11298459257","observation_id":"aa12fe3b-79f9-48ce-9a3a-ef244e6219f7","resolution":{"observed_at":"2026-08-12T20:14:27.653762Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1145/3620667","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:25.452321Z","title":null,"venue":null,"work_id":"75d54929-aa48-43a1-aa22-b029a5ce0e8f","year":2023},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:24.888432Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:09a9205b233b7e2b780aa5e3268560c8acf1ae159aa85a3ed66907843aa7c289","observation_id":"b197a880-88c2-4197-a14a-f3da73ff797c","resolution":{"observed_at":"2026-08-12T20:14:25.456988Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2021.30884","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:27.561031Z","title":null,"venue":null,"work_id":"d068284d-5a95-4ebb-af13-c61671821b2e","year":2022},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:24.905914Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:4eca290b2416399da77debbebcd1cfe824ff975174d6318fab47bf68482897f3","observation_id":"6d30b0b3-274d-48bf-95a4-3e108b2e05ab","resolution":{"observed_at":"2026-08-12T20:14:27.566618Z","resolver_source":"raw_fallback","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2210.10133","last_updated":"2024-06-17T21:38:42Z","snapshot_observed_at":"2026-08-13T14:02:30.585589Z","submitted_at":"2022-10-18T20:06:06Z","title":"Efficient Privacy-Preserving Machine Learning with Lightweight Trusted Hardware","version":4},"cited_work":{"arxiv_id":"2210.10133","doi":null,"metadata_source":"pith","pith_arxiv_id":"2210.10133","snapshot_observed_at":"2026-08-12T20:14:27.488196Z","title":"Efficient Privacy-Preserving Machine Learning with Lightweight Trusted Hardware","venue":"cs.CR","work_id":"290645d5-5639-4c7b-881f-ae028514f0cf","year":2022},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:24.910390Z"},"links":{"cited_paper":"/paper/2210.10133","citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:c08290c10a77cae7105389ac65e0ef4c4474b399ca9eb4f6abab70583639e191","observation_id":"ad61212f-8063-4ff1-910a-3c68cd4976db","resolution":{"observed_at":"2026-08-12T20:14:27.492232Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"5970.31961","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:27.627781Z","title":"Edward Suh","venue":null,"work_id":"24c49f27-f794-4dba-9833-34c8097ddc00","year":2018},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:24.901891Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:2215ff3fe65d2d4fa1b40be6a9cee09d6d049cf6557bd8f77a8b32ed7c71feb5","observation_id":"9c50dd22-863a-4f97-bf8d-0adf012412c3","resolution":{"observed_at":"2026-08-12T20:14:27.636964Z","resolver_source":"raw_fallback","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:24.919059Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:24.919059Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:c32076a97ad763a9ad5292024c10ea4f641bbc946178176da1bba67ecf8fb428","observation_id":"2bd4e6db-d930-440e-8c53-a345ec6689ff","resolution":{"observed_at":"2026-08-12T20:14:24.919059Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:24.923057Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:24.923057Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:d8048e22261666ccf57f7482e35da94551cebbc03356c343c5aa4329aefd62ef","observation_id":"78da335d-8b1b-406c-97b8-3362d19300ec","resolution":{"observed_at":"2026-08-12T20:14:24.923057Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:24.914743Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:24.914743Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:e9e09361269973196ba72aaac52cc2b6d891f3ac9f85962ad3d64069608f802c","observation_id":"1cd895ae-1f00-4cf5-9b35-d841f18a8fa0","resolution":{"observed_at":"2026-08-12T20:14:24.914743Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:24.930476Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:24.930476Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:790a8e778fc99a3dabb21647ad31392369b79eceb7b8d1d04a330cf841b18aa1","observation_id":"a367a175-5ddc-47ad-8811-db89d8bfe558","resolution":{"observed_at":"2026-08-12T20:14:24.930476Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:24.934477Z","title":"Chandrakasan","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:24.934477Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:3ac4ae8349797d19714d9c2fde067a1035457543f0fd66d443ef27c54f66d91d","observation_id":"fa02125c-d018-4342-9177-f2a2ef5acc4c","resolution":{"observed_at":"2026-08-12T20:14:24.934477Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:24.926740Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:24.926740Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:0f5b1076a18ec2eea2cdd3803b51b415116556dbd8a4cab3d31fcd96d8ae73df","observation_id":"eb1fd2e1-31c7-420c-9838-3d940c34b129","resolution":{"observed_at":"2026-08-12T20:14:24.926740Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:24.943191Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:24.943191Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:2ab889caa9050e1a4449a954c360f61c1647bbd59a8ec52720aa6d3eca23d057","observation_id":"ea665e22-b3b2-4802-a553-01af658663e3","resolution":{"observed_at":"2026-08-12T20:14:24.943191Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2006.05336","last_updated":"2020-06-09T15:17:21Z","snapshot_observed_at":"2026-08-14T13:12:38.498869Z","submitted_at":"2020-06-09T15:17:21Z","title":"On the Effectiveness of Regularization Against Membership Inference Attacks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.05336","snapshot_observed_at":"2026-08-12T20:14:24.947478Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:24.947478Z"},"links":{"cited_paper":"/paper/2006.05336","citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:bf8ebfde75020fcb44876fcccfd204cb8d333319cce2040f31faccc3f8303759","observation_id":"728f9154-3e8f-4b9c-9a1c-fe6a2ed3100d","resolution":{"observed_at":"2026-08-12T20:14:24.947478Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:24.939172Z","title":null,"venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:24.939172Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:170d408b2b67e5c4edd8b471b6c6cbd372f53daf61ae48179f2344eb2b8f7226","observation_id":"9bc0a84d-7037-4e48-8eae-9906996a4eb5","resolution":{"observed_at":"2026-08-12T20:14:24.939172Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:24.956557Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:24.956557Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:8953b4c2bb92e32d0e5db0a9f1a55670de023d3d2e34d06c90734d964a2985a3","observation_id":"337f2da7-cdd0-4881-82e1-cba1155f5f37","resolution":{"observed_at":"2026-08-12T20:14:24.956557Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:24.961644Z","title":null,"venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:24.961644Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:df28194c9d876ab5943cdc705079780752d61c2f2798f477ef1deaec697736db","observation_id":"2128416f-181f-4d11-8b80-1a287671cb7e","resolution":{"observed_at":"2026-08-12T20:14:24.961644Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:24.952467Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:24.952467Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:0bd7323713efbd85017d8eea7f2826977c23b4ca69d847a2614d59c3e01a258e","observation_id":"858abe51-cf85-4c30-b2fb-1446143f1788","resolution":{"observed_at":"2026-08-12T20:14:24.952467Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:24.970877Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:24.970877Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:9e0a973bd043693565363ab91a0780cf540f7076962f9ec10f7c14a93dc629ee","observation_id":"03c31983-5997-42ab-885c-d7c2516b4183","resolution":{"observed_at":"2026-08-12T20:14:24.970877Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"8935.32689","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:27.276649Z","title":null,"venue":null,"work_id":"788096e7-49d9-4713-8d91-0d3d592be857","year":2018},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:24.975594Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:83e8c0ac6cbda3f6163391c10dfd85c02ed69ac9f3e448dc40a5d2acc26eaaeb","observation_id":"ab810b80-d82c-4e02-b0ea-946477018765","resolution":{"observed_at":"2026-08-12T20:14:27.282563Z","resolver_source":"raw_fallback","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:24.966108Z","title":null,"venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:24.966108Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:93a7aeb44d6ecc72fe4e5fc005d114072c39b5ecc258ad8a24681ac413353f5c","observation_id":"fd256c4e-ce67-4e00-8965-0b139e3bbba8","resolution":{"observed_at":"2026-08-12T20:14:24.966108Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:24.984053Z","title":"Molloy, and Dong Su","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:24.984053Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:388fd050cdaf1964fcf12c370efba0b23566e0ef3cd47069b4f59d9e9fa4404f","observation_id":"f7555294-4fef-4dff-a571-ee8e1631f93e","resolution":{"observed_at":"2026-08-12T20:14:24.984053Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:24.987806Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:24.987806Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:3ac60f0c6b12bf98c4e0e1be92d0c18d38d47e1f6b19bb1064c8ac00dd311020","observation_id":"5b4833bf-c71d-485f-9aa5-ab355128e852","resolution":{"observed_at":"2026-08-12T20:14:24.987806Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:24.979692Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:24.979692Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:05379715117491aa0b7708984c3b1e9fe748fc8026fcd2fa648e7fc01baafa47","observation_id":"aa22915e-ba1e-4111-b736-e013ff2efc0c","resolution":{"observed_at":"2026-08-12T20:14:24.979692Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:24.995559Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:24.995559Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:9608672960074e7533c7824304fc74de7df57e89b86d9313f283e38947bf6153","observation_id":"31006564-d1b1-4d7c-8f70-f0ba738b99f3","resolution":{"observed_at":"2026-08-12T20:14:24.995559Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:24.999820Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:24.999820Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:08a0190b155f2b12ea8c35da243dabe281d38b85467f82f7162eb69b13f6ad7f","observation_id":"7c0cbd72-f705-4463-ac3c-2f8578314ed2","resolution":{"observed_at":"2026-08-12T20:14:24.999820Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:24.991458Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:24.991458Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:2dbb15c41ca024c4f0ca70e95ae3e9b7bb6110c1acc7f062d82576b3963e0f9e","observation_id":"f10ceab6-d963-4f71-b911-584ba916fe0d","resolution":{"observed_at":"2026-08-12T20:14:24.991458Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:25.008008Z","title":"Zomaya, and Minyi Guo","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:25.008008Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:46b3e857ac66a9d0fe9a4828b3734009bc0ba91a5b5c26b1e05495cbc265eafe","observation_id":"3a6f5ff7-ef35-4352-88a4-3531ab111517","resolution":{"observed_at":"2026-08-12T20:14:25.008008Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:25.011605Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:25.011605Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:7f1dac3f0668cc3f6a25e150c5c8c190f8782f310d12d54bfdd51c258bef6061","observation_id":"2b552ec7-1d09-45a0-b2bd-341621e2e7eb","resolution":{"observed_at":"2026-08-12T20:14:25.011605Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.11121","last_updated":"2024-11-21T02:16:53Z","snapshot_observed_at":"2026-08-14T22:04:00.219110Z","submitted_at":"2024-04-17T07:08:45Z","title":"TransLinkGuard: Safeguarding Transformer Models Against Model Stealing in Edge Deployment","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.11121","snapshot_observed_at":"2026-08-12T20:14:25.003751Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:25.003751Z"},"links":{"cited_paper":"/paper/2404.11121","citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:8c4ffb5f42d853edf8fd901c87120591700fc1e70ee45cb1f4f084d74320097a","observation_id":"b6b3514c-e7f8-439e-8e7e-dca534b20f04","resolution":{"observed_at":"2026-08-12T20:14:25.003751Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:25.018966Z","title":"Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Dollár, and C","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:25.018966Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:166956e22575d90c85e006de654b35986cf956ac51e1df53074336f272d298ae","observation_id":"57edd652-09a6-4ed6-99ff-03e73311b3f0","resolution":{"observed_at":"2026-08-12T20:14:25.018966Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:25.022775Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:25.022775Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:6e067a98c6275e75c4d15af8d85178dcb45de51530a18c6ed4fa0970ba1a8b8f","observation_id":"ab6708d9-54ab-4a9e-9a84-4080ef2e651b","resolution":{"observed_at":"2026-08-12T20:14:25.022775Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:25.015162Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:25.015162Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:5f786e8da56366c74d20ddc105808b0f421edc1cb0a8924038e53350d3e95cc4","observation_id":"29371ebe-ce0b-4807-a8e7-ad245a8b1e3b","resolution":{"observed_at":"2026-08-12T20:14:25.015162Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:25.034091Z","title":null,"venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:25.034091Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:16c3b173f0399893b0dafa94b0d2e41e82f1e84d15bc94aeca70ff68dcc40d10","observation_id":"d4e164a7-4b63-4cda-9ec0-9f3e2d15b0cd","resolution":{"observed_at":"2026-08-12T20:14:25.034091Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:25.038000Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:25.038000Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:b971ce23fd10078c3da12fe4326364eb233a1ee729fcb2f0219af9bbc3c1bb55","observation_id":"f2ade33a-c858-4c95-926e-20eb7f83617a","resolution":{"observed_at":"2026-08-12T20:14:25.038000Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:25.026561Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:25.026561Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:f3d2708f7a98c68713095bed060b895216d2668e90ba4696576a1ececac2d4b2","observation_id":"0a3b716e-89dd-455d-bba2-96c798b2fedc","resolution":{"observed_at":"2026-08-12T20:14:25.026561Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:25.030496Z","title":"In 2021 IEEE Symposium on Security and Privacy (SP)","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:25.030496Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:bde38f40ab98486dc6ace1ae03431de86abe29e4dd6d788e7236bcbc53d24a86","observation_id":"afb90b72-b337-4cf9-8c70-292b5a3706fe","resolution":{"observed_at":"2026-08-12T20:14:25.030496Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:25.049578Z","title":null,"venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:25.049578Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:e88cf489f1de0dd0798be34a68db5465f4da4ef20aa9b7b817da2e1e433dc703","observation_id":"7b58f324-080c-4e82-9148-89c7b4bcc25c","resolution":{"observed_at":"2026-08-12T20:14:25.049578Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:25.053164Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:25.053164Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:8160e059694897ca2d61765d34869bf8fc00d8b4b9df3b0035152a4963315afb","observation_id":"3fdffa5c-b24f-4022-97af-528065c28832","resolution":{"observed_at":"2026-08-12T20:14:25.053164Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.09489","last_updated":"2023-11-16T01:21:19Z","snapshot_observed_at":"2026-08-13T05:24:16.999683Z","submitted_at":"2023-11-16T01:21:19Z","title":"MirrorNet: A TEE-Friendly Framework for Secure On-device DNN Inference","version":1},"cited_work":{"arxiv_id":"2311.09489","doi":"10.48550/arxiv.2311.09489","metadata_source":"pith","pith_arxiv_id":"2311.09489","snapshot_observed_at":"2026-08-13T00:16:21.800782Z","title":"MirrorNet: A TEE-Friendly Framework for Secure On-device DNN Inference","venue":"cs.CR","work_id":"2ca2b590-ed84-4333-9222-e793e530a4bc","year":2023},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:25.041759Z"},"links":{"cited_paper":"/paper/2311.09489","citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:3e89693867d841a7cfc357e89f9f113158792274c3bca83b41b7027083c9eccb","observation_id":"ef0945c2-b8e9-469f-ad05-0ce86dc0c5fd","resolution":{"observed_at":"2026-08-12T20:14:25.431814Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:25.045814Z","title":null,"venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":91,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:25.045814Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:3e253b24e388d159ac5007dc85f7f9b83c4f2567705400b447d56454edc10d4e","observation_id":"8af40926-cfff-40ad-b1c4-08ca27e3e583","resolution":{"observed_at":"2026-08-12T20:14:25.045814Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:25.065247Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":92,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:25.065247Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:ae50a9a1484cb37e6d116f3bfc2e2948fb86a7e08b3cdf65bb1e709db647d878","observation_id":"c26bfcfb-b284-4a75-91cb-5c4eb267c5db","resolution":{"observed_at":"2026-08-12T20:14:25.065247Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:25.069971Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":93,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:25.069971Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:f16abfa2dfd953b156f9c0d2a471c65b734af831a954c4600c0256c7eca07dfb","observation_id":"c640dfac-4190-4320-87d0-602ac47b0632","resolution":{"observed_at":"2026-08-12T20:14:25.069971Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:25.057208Z","title":"Rozas, Hisham Shafi, Vedvyas Shanbhogue, and Uday R","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":94,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:25.057208Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:c6e225af67e4317ed69cc145dc55eb709e7adf597e97a4a85aba8f44cf3870aa","observation_id":"0a6e27a4-d7b2-45de-901a-624d3959a7c2","resolution":{"observed_at":"2026-08-12T20:14:25.057208Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:25.060949Z","title":"Dibbo, Ehsanul Kabir, Ninghui Li, and Elisa Bertino","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":95,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:25.060949Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:c7035676d27d3f18a787174070541ad1ad7b4cce8203bbdf652f01f85d0d18bb","observation_id":"b155e48a-63ff-4954-ae5a-e4974c99e62e","resolution":{"observed_at":"2026-08-12T20:14:25.060949Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:25.083162Z","title":"Tullsen, and Hadi Esmaeilzadeh","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":96,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:25.083162Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:4936411a8901c35e4bef82ae7e71a70950e02e1f477d6c5550293844d239af1a","observation_id":"000e036e-459d-40ed-a963-889d5d9ff120","resolution":{"observed_at":"2026-08-12T20:14:25.083162Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:25.086947Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":97,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:25.086947Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:cd4ac2fa3752159f0218fc4454df4f0fda5d30844f23803fdefadec7130a3318","observation_id":"399c3ca5-2309-4477-8f14-352f61f594cb","resolution":{"observed_at":"2026-08-12T20:14:25.086947Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:25.074308Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":98,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:25.074308Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:68284f44886c6702554d5f239b3fcecf276d0566ec0fe9580ba11bac9649c8bc","observation_id":"babd23f8-c1b0-46d0-8ca7-c6e7d2fe13cf","resolution":{"observed_at":"2026-08-12T20:14:25.074308Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:25.078726Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":99,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:25.078726Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:5bceef28c876b3db0426d143244a82d0bfa41cff1c6d5e20b756c44ec41850f9","observation_id":"df093e89-a5fa-401b-abc7-51b3652abe27","resolution":{"observed_at":"2026-08-12T20:14:25.078726Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:25.097576Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":100,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:25.097576Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:279eac48976d870616bbf88276b3779ca43baf3d809e5bda99c194261c38a0e0","observation_id":"8c5b115d-b633-4a9d-b453-c01c02f9bd15","resolution":{"observed_at":"2026-08-12T20:14:25.097576Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:25.101829Z","title":"Oswald, Flavio D","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":101,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:25.101829Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:ea15706ffb15dcb729d53612620063017012f90fd301caf0cbbf5ccfeee8cc2a","observation_id":"8516e641-2637-4fc0-ad7f-8031570f320c","resolution":{"observed_at":"2026-08-12T20:14:25.101829Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:14:25.090345Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","version":1},"reference_index":102,"source":"pdf_text","source_observed_at":"2026-08-12T20:14:25.090345Z"},"links":{"citing_paper":"/paper/2411.09945"},"observation_digest":"sha256:2fd6f656c0e6a052639a5836b7d72b7694fa68fb94f0607b1b1ff189b7cffcf4","observation_id":"be3869f2-f44b-4b81-a73c-900b5e59737a","resolution":{"observed_at":"2026-08-12T20:14:25.090345Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2411.09945","last_updated":"2024-11-15T04:52:11Z","latest_version":1,"primary_category":"cs.CR","snapshot_observed_at":"2026-08-14T10:34:40.308851Z","submitted_at":"2024-11-15T04:52:11Z","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models"},"reference_resolution":{"displayed":100,"state_counts":{"malformed_identifier":2,"metadata_mismatch":5,"parse_uncertain":0,"unresolved":88,"verified_exact":5,"verified_fuzzy":0},"total_outbound_references":168},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"thesis":"As of 16 August 2026, this Paper Citation Record lists 100 of 168 outbound references and 2 inbound Pith citation observations for arXiv:2411.09945."}