{"as_of":"2026-08-12T20:20:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:3b709ce8de2bba7a0593e8a5001eec3e0deb5f30fe874aa4c47e7453c6743b0d","coverage":[{"denominator":59,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":59,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-10T22:48:43.180083Z","state":"measured"},{"denominator":59,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":59,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-12T06:34:41.77262+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2501.00824/citation-record","integrity":"/paper/2501.00824/integrity","json":"/paper/2501.00824/citation-record.json","paper":"/paper/2501.00824"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2411.07114","last_updated":"2024-11-11T16:41:22Z","snapshot_observed_at":"2026-08-10T19:09:24.450289Z","submitted_at":"2024-11-11T16:41:22Z","title":"TinyML Security: Exploring Vulnerabilities in Resource-Constrained Machine Learning Systems","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.07114","snapshot_observed_at":"2026-08-10T22:48:42.106137Z","title":"Tinyml security: Explor- ing vulnerabilities in resource-constrained machine learning systems,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.00824","last_updated":"2025-06-20T14:59:56Z","snapshot_observed_at":"2026-08-11T21:13:43.994902Z","submitted_at":"2025-01-01T13:00:01Z","title":"How Breakable Is Privacy: Probing and Resisting Model Inversion Attacks in Collaborative Inference","version":7},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-10T22:48:42.106137Z"},"links":{"cited_paper":"/paper/2411.07114","citing_paper":"/paper/2501.00824"},"observation_digest":"sha256:80db98e63cffb5248521eb096bbe9772b63be3b8fd5474ec407de65a6327ee67","observation_id":"f1971fc3-eca1-49ac-8d94-be3f223dbdf4","resolution":{"observed_at":"2026-08-10T22:48:42.106137Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T22:48:44.260767Z","title":"Collaborative inference for ai- empowered iot devices,","venue":null,"work_id":"3128a349-8420-4734-bb06-87d50d4ed593","year":2022},"citing_paper":{"arxiv_id":"2501.00824","last_updated":"2025-06-20T14:59:56Z","snapshot_observed_at":"2026-08-11T21:13:43.994902Z","submitted_at":"2025-01-01T13:00:01Z","title":"How Breakable Is Privacy: Probing and Resisting Model Inversion Attacks in Collaborative Inference","version":7},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-10T22:48:42.132745Z"},"links":{"citing_paper":"/paper/2501.00824"},"observation_digest":"sha256:90e2d9407961ade6a0b62cd043daec25f4dc97cf40a3a9d231a36fe2dc528fbc","observation_id":"30a520d0-7c2e-4310-8dac-3041ba6d9f58","resolution":{"observed_at":"2026-08-10T22:48:44.266029Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T22:48:44.243221Z","title":"Collaborative in- ference via ensembles on the edge,","venue":null,"work_id":"2830c8ca-5058-49b2-8318-9b6f94d9eb08","year":2021},"citing_paper":{"arxiv_id":"2501.00824","last_updated":"2025-06-20T14:59:56Z","snapshot_observed_at":"2026-08-11T21:13:43.994902Z","submitted_at":"2025-01-01T13:00:01Z","title":"How Breakable Is Privacy: Probing and Resisting Model Inversion Attacks in Collaborative Inference","version":7},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-10T22:48:42.195045Z"},"links":{"citing_paper":"/paper/2501.00824"},"observation_digest":"sha256:dd0f7fe54aa387216efb6930e8e7d567fda5b6faa5e05c4252e6d4471e12ef79","observation_id":"58468491-fec1-47b5-87a4-d1d198f06f36","resolution":{"observed_at":"2026-08-10T22:48:44.249096Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T22:48:44.225685Z","title":"Elastic collaborative edge intelligence for uav swarm: Architecture, challenges, and opportunities,","venue":null,"work_id":"58cff566-aa23-4971-be2d-dac649df29d2","year":2024},"citing_paper":{"arxiv_id":"2501.00824","last_updated":"2025-06-20T14:59:56Z","snapshot_observed_at":"2026-08-11T21:13:43.994902Z","submitted_at":"2025-01-01T13:00:01Z","title":"How Breakable Is Privacy: Probing and Resisting Model Inversion Attacks in Collaborative Inference","version":7},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-10T22:48:42.230759Z"},"links":{"citing_paper":"/paper/2501.00824"},"observation_digest":"sha256:8537110fab0776140a4c4a9c83dea7f35c9c972320aa2f6914c692ff75ba472c","observation_id":"513a2a35-0792-4101-8e30-681a2a871796","resolution":{"observed_at":"2026-08-10T22:48:44.231124Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T22:48:44.208864Z","title":null,"venue":null,"work_id":"24b6044c-a6e9-4ccd-afb9-acdfc8e03889","year":2024},"citing_paper":{"arxiv_id":"2501.00824","last_updated":"2025-06-20T14:59:56Z","snapshot_observed_at":"2026-08-11T21:13:43.994902Z","submitted_at":"2025-01-01T13:00:01Z","title":"How Breakable Is Privacy: Probing and Resisting Model Inversion Attacks in Collaborative Inference","version":7},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-10T22:48:42.273839Z"},"links":{"citing_paper":"/paper/2501.00824"},"observation_digest":"sha256:5eafc40c2b823cd1523f0a09f790549440e848dc45426b19de01c30e856b74ad","observation_id":"fc890f28-b2ba-4cd6-890d-675c457a4e3c","resolution":{"observed_at":"2026-08-10T22:48:44.213648Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T22:48:42.299848Z","title":"Model inversion attacks against collaborative inference,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2501.00824","last_updated":"2025-06-20T14:59:56Z","snapshot_observed_at":"2026-08-11T21:13:43.994902Z","submitted_at":"2025-01-01T13:00:01Z","title":"How Breakable Is Privacy: Probing and Resisting Model Inversion Attacks in Collaborative Inference","version":7},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-10T22:48:42.299848Z"},"links":{"citing_paper":"/paper/2501.00824"},"observation_digest":"sha256:b016c2803eca91d279e77dffb32b202821a323626c6d152e18fd202054088417","observation_id":"903da55b-63d6-47da-a0bf-7c40fb1343c4","resolution":{"observed_at":"2026-08-10T22:48:42.299848Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T22:48:44.179595Z","title":"Measuring data reconstruction defenses in collaborative inference systems,","venue":null,"work_id":"c8e841e1-d642-4a3a-9d22-c23f3a258b75","year":2022},"citing_paper":{"arxiv_id":"2501.00824","last_updated":"2025-06-20T14:59:56Z","snapshot_observed_at":"2026-08-11T21:13:43.994902Z","submitted_at":"2025-01-01T13:00:01Z","title":"How Breakable Is Privacy: Probing and Resisting Model Inversion Attacks in Collaborative Inference","version":7},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-10T22:48:42.306940Z"},"links":{"citing_paper":"/paper/2501.00824"},"observation_digest":"sha256:ed2b43fe1ad204d9352fb37124400fcfa61a03087e0f20b257f768e2c7a037bb","observation_id":"b261af70-0dcc-4b89-91fd-a6d834fef84d","resolution":{"observed_at":"2026-08-10T22:48:44.185430Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T22:48:44.162519Z","title":"Ginver: Generative model inversion attacks against collaborative inference,","venue":null,"work_id":"1ec07f88-0171-481c-84a5-7d001b6b69ac","year":2023},"citing_paper":{"arxiv_id":"2501.00824","last_updated":"2025-06-20T14:59:56Z","snapshot_observed_at":"2026-08-11T21:13:43.994902Z","submitted_at":"2025-01-01T13:00:01Z","title":"How Breakable Is Privacy: Probing and Resisting Model Inversion Attacks in Collaborative Inference","version":7},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-10T22:48:42.312910Z"},"links":{"citing_paper":"/paper/2501.00824"},"observation_digest":"sha256:72ddca933c30b1c6f74d38015c1289ce18ad7859665a3eeacf87576a5241f148","observation_id":"913c3aa5-207b-4912-9868-0ab1333fb3af","resolution":{"observed_at":"2026-08-10T22:48:44.168037Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T22:48:42.320750Z","title":"Member- ship inference attacks and generalization: A causal perspective,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.00824","last_updated":"2025-06-20T14:59:56Z","snapshot_observed_at":"2026-08-11T21:13:43.994902Z","submitted_at":"2025-01-01T13:00:01Z","title":"How Breakable Is Privacy: Probing and Resisting Model Inversion Attacks in Collaborative Inference","version":7},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-10T22:48:42.320750Z"},"links":{"citing_paper":"/paper/2501.00824"},"observation_digest":"sha256:15aadc3fbf41549c73fdb42a15e5f13c61d3bef517acbf368f7ac4bc18fe82b7","observation_id":"659327e1-82ea-49c1-aae8-0733fc9755a2","resolution":{"observed_at":"2026-08-10T22:48:42.320750Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T22:48:44.132006Z","title":"Neural network inversion in adversarial setting via background knowledge alignment,","venue":null,"work_id":"7548eee6-782d-46ba-8308-8c4c382a93c9","year":2019},"citing_paper":{"arxiv_id":"2501.00824","last_updated":"2025-06-20T14:59:56Z","snapshot_observed_at":"2026-08-11T21:13:43.994902Z","submitted_at":"2025-01-01T13:00:01Z","title":"How Breakable Is Privacy: Probing and Resisting Model Inversion Attacks in Collaborative Inference","version":7},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-10T22:48:42.334419Z"},"links":{"citing_paper":"/paper/2501.00824"},"observation_digest":"sha256:746144e76f8218e0c9d06de706ac4ed00ce17447141baf0474a902aaa4ab9dfe","observation_id":"75aea5a3-74de-4f66-857c-aee2d0efc3fc","resolution":{"observed_at":"2026-08-10T22:48:44.138516Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T22:48:44.113334Z","title":"The secret revealer: Generative model- inversion attacks against deep neural networks,","venue":null,"work_id":"3206daa2-8a63-43de-b397-316fb1884ff5","year":2020},"citing_paper":{"arxiv_id":"2501.00824","last_updated":"2025-06-20T14:59:56Z","snapshot_observed_at":"2026-08-11T21:13:43.994902Z","submitted_at":"2025-01-01T13:00:01Z","title":"How Breakable Is Privacy: Probing and Resisting Model Inversion Attacks in Collaborative Inference","version":7},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-10T22:48:42.340080Z"},"links":{"citing_paper":"/paper/2501.00824"},"observation_digest":"sha256:555f7db634f63c9da7e769f15d77d1bbf83f7bfab7da8a83012811dfcf3d8923","observation_id":"94d4506d-5f03-4a31-8134-117e14f24b9f","resolution":{"observed_at":"2026-08-10T22:48:44.119339Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T22:48:44.093904Z","title":"Unstoppable attack: Label-only model inversion via conditional diffusion model,","venue":null,"work_id":"39d339bc-3ade-4e11-bf50-27cf9cf7ca18","year":2024},"citing_paper":{"arxiv_id":"2501.00824","last_updated":"2025-06-20T14:59:56Z","snapshot_observed_at":"2026-08-11T21:13:43.994902Z","submitted_at":"2025-01-01T13:00:01Z","title":"How Breakable Is Privacy: Probing and Resisting Model Inversion Attacks in Collaborative Inference","version":7},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-10T22:48:42.346501Z"},"links":{"citing_paper":"/paper/2501.00824"},"observation_digest":"sha256:359c8f3accfcd5053c21159e6f82a4c9cb03221e5ee724fffc75b88bcaa625e2","observation_id":"4843144e-c722-4606-9c53-d86eb4055969","resolution":{"observed_at":"2026-08-10T22:48:44.100454Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T22:48:44.076117Z","title":"Privacy in pharmacogenetics: An {End-to-End} case study of personalized warfarin dosing,","venue":null,"work_id":"b716f247-ab56-4816-9017-1cccbe925064","year":2014},"citing_paper":{"arxiv_id":"2501.00824","last_updated":"2025-06-20T14:59:56Z","snapshot_observed_at":"2026-08-11T21:13:43.994902Z","submitted_at":"2025-01-01T13:00:01Z","title":"How Breakable Is Privacy: Probing and Resisting Model Inversion Attacks in Collaborative Inference","version":7},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-10T22:48:42.352366Z"},"links":{"citing_paper":"/paper/2501.00824"},"observation_digest":"sha256:001d7305dfad1822a25ecfa7290afcb73693349b62cb35bd9f55d0096f69ec8f","observation_id":"a510f3ba-7856-4c00-8b97-e20083e74110","resolution":{"observed_at":"2026-08-10T22:48:44.082041Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T22:48:44.057580Z","title":"Are your sensitive at- tributes private? novel model inversion attribute inference attacks on classification models,","venue":null,"work_id":"88e4f5b6-5eb1-4d36-a4ff-c2af7bb8916c","year":2022},"citing_paper":{"arxiv_id":"2501.00824","last_updated":"2025-06-20T14:59:56Z","snapshot_observed_at":"2026-08-11T21:13:43.994902Z","submitted_at":"2025-01-01T13:00:01Z","title":"How Breakable Is Privacy: Probing and Resisting Model Inversion Attacks in Collaborative Inference","version":7},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-10T22:48:42.357917Z"},"links":{"citing_paper":"/paper/2501.00824"},"observation_digest":"sha256:71d8f356e2f70c5b7a34d7438b2f69cc0cd6df2d6fb3aa0c03c4daf9551d4239","observation_id":"b95c6370-3748-4415-91a7-1fafdb535050","resolution":{"observed_at":"2026-08-10T22:48:44.063247Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T22:48:44.036239Z","title":"Privacy-preserving autoencoder for col- laborative object detection,","venue":null,"work_id":"909a88e9-3b0c-461d-98b1-15b48092717a","year":2024},"citing_paper":{"arxiv_id":"2501.00824","last_updated":"2025-06-20T14:59:56Z","snapshot_observed_at":"2026-08-11T21:13:43.994902Z","submitted_at":"2025-01-01T13:00:01Z","title":"How Breakable Is Privacy: Probing and Resisting Model Inversion Attacks in Collaborative Inference","version":7},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-10T22:48:42.362444Z"},"links":{"citing_paper":"/paper/2501.00824"},"observation_digest":"sha256:51d26b0efa64c018696ff61739c6eaf17718944e3090c348688d86a8c2867b73","observation_id":"eee8171c-3da7-41f9-80d4-b046adad16f4","resolution":{"observed_at":"2026-08-10T22:48:44.042706Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T22:48:44.017949Z","title":"Attacking and protecting data privacy in edge–cloud collaborative inference systems,","venue":null,"work_id":"c8f03e5b-7be0-4522-ad97-dfe4d6d22624","year":2020},"citing_paper":{"arxiv_id":"2501.00824","last_updated":"2025-06-20T14:59:56Z","snapshot_observed_at":"2026-08-11T21:13:43.994902Z","submitted_at":"2025-01-01T13:00:01Z","title":"How Breakable Is Privacy: Probing and Resisting Model Inversion Attacks in Collaborative Inference","version":7},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-10T22:48:42.367775Z"},"links":{"citing_paper":"/paper/2501.00824"},"observation_digest":"sha256:919be72347061d22de73a66f12d1ac18cab82101e3bafe685f2aefc2c0174305","observation_id":"38ec479a-2aa0-4559-b169-aed82dd08ed2","resolution":{"observed_at":"2026-08-10T22:48:44.023402Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2212.06428","last_updated":"2022-12-13T08:36:11Z","snapshot_observed_at":"2026-08-12T02:29:59.138368Z","submitted_at":"2022-12-13T08:36:11Z","title":"Privacy-preserving Security Inference Towards Cloud-Edge Collaborative Using Differential Privacy","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.06428","snapshot_observed_at":"2026-08-10T22:48:42.372901Z","title":"Privacy-preserving security in- ference towards cloud-edge collaborative using differential privacy,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.00824","last_updated":"2025-06-20T14:59:56Z","snapshot_observed_at":"2026-08-11T21:13:43.994902Z","submitted_at":"2025-01-01T13:00:01Z","title":"How Breakable Is Privacy: Probing and Resisting Model Inversion Attacks in Collaborative Inference","version":7},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-10T22:48:42.372901Z"},"links":{"cited_paper":"/paper/2212.06428","citing_paper":"/paper/2501.00824"},"observation_digest":"sha256:2005f594710fda3687108fa0dc107fb8af0da01db2c5632d854c6d6e7b0346d4","observation_id":"965128de-ca1f-4c6a-8712-1fef13f3065e","resolution":{"observed_at":"2026-08-10T22:48:42.372901Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T22:48:43.999051Z","title":"Bilateral dependency optimization: Defending against model-inversion attacks,","venue":null,"work_id":"2e68a3c8-da06-490a-8d9c-ded17ec886b7","year":2022},"citing_paper":{"arxiv_id":"2501.00824","last_updated":"2025-06-20T14:59:56Z","snapshot_observed_at":"2026-08-11T21:13:43.994902Z","submitted_at":"2025-01-01T13:00:01Z","title":"How Breakable Is Privacy: Probing and Resisting Model Inversion Attacks in Collaborative Inference","version":7},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-10T22:48:42.377894Z"},"links":{"citing_paper":"/paper/2501.00824"},"observation_digest":"sha256:283b3de7e99568e87dc220a8a67e35ac2e1f13f75e7a9dd5648696b6ca67bff9","observation_id":"26abc8e5-a1e2-44da-80f9-fcb877c5cd1c","resolution":{"observed_at":"2026-08-10T22:48:44.004601Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T22:48:43.979657Z","title":"Privacy-preserving task-oriented semantic communications against model inversion attacks,","venue":null,"work_id":"fbc4e5e5-46db-462e-b02b-068441966d25","year":2024},"citing_paper":{"arxiv_id":"2501.00824","last_updated":"2025-06-20T14:59:56Z","snapshot_observed_at":"2026-08-11T21:13:43.994902Z","submitted_at":"2025-01-01T13:00:01Z","title":"How Breakable Is Privacy: Probing and Resisting Model Inversion Attacks in Collaborative Inference","version":7},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-10T22:48:42.382964Z"},"links":{"citing_paper":"/paper/2501.00824"},"observation_digest":"sha256:5c1ee5bccf45341e833c592e6b0fb595cb119e8aad38cbd059e594188bbc8280","observation_id":"994aa6d1-0407-4e4a-b8e7-75bf4b816892","resolution":{"observed_at":"2026-08-10T22:48:43.986306Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T22:48:43.957759Z","title":"Patrol: Privacy-oriented pruning for collaborative inference against model inversion attacks,","venue":null,"work_id":"377e2827-6818-4a93-a334-b1499b568c62","year":2024},"citing_paper":{"arxiv_id":"2501.00824","last_updated":"2025-06-20T14:59:56Z","snapshot_observed_at":"2026-08-11T21:13:43.994902Z","submitted_at":"2025-01-01T13:00:01Z","title":"How Breakable Is Privacy: Probing and Resisting Model Inversion Attacks in Collaborative Inference","version":7},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-10T22:48:42.455448Z"},"links":{"citing_paper":"/paper/2501.00824"},"observation_digest":"sha256:a5857b4773890dd26d48bd8ee828804d13cfd0bc98a4f460df360acdadd12bf5","observation_id":"78026bce-1836-47fa-8bca-22d9e4b4a4ad","resolution":{"observed_at":"2026-08-10T22:48:43.963620Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T22:48:43.938624Z","title":"Improving robustness to model inver- sion attacks via mutual information regularization,","venue":null,"work_id":"85348958-e6c7-4be8-824d-2f6aaeb8e5df","year":2021},"citing_paper":{"arxiv_id":"2501.00824","last_updated":"2025-06-20T14:59:56Z","snapshot_observed_at":"2026-08-11T21:13:43.994902Z","submitted_at":"2025-01-01T13:00:01Z","title":"How Breakable Is Privacy: Probing and Resisting Model Inversion Attacks in Collaborative Inference","version":7},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-10T22:48:42.525733Z"},"links":{"citing_paper":"/paper/2501.00824"},"observation_digest":"sha256:a4d6b7ac1d27782fd54c1d925bc39f220c1ad36ec48adc72374e68eee8a1bc29","observation_id":"1e6302a6-b151-465d-890e-bb449110e985","resolution":{"observed_at":"2026-08-10T22:48:43.944471Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T22:48:43.917707Z","title":"Not all features are equal: Discovering essential features for preserving prediction privacy,","venue":null,"work_id":"82e5755e-5923-493b-bcb7-aa57b38f19a0","year":2021},"citing_paper":{"arxiv_id":"2501.00824","last_updated":"2025-06-20T14:59:56Z","snapshot_observed_at":"2026-08-11T21:13:43.994902Z","submitted_at":"2025-01-01T13:00:01Z","title":"How Breakable Is Privacy: Probing and Resisting Model Inversion Attacks in Collaborative Inference","version":7},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-10T22:48:42.627177Z"},"links":{"citing_paper":"/paper/2501.00824"},"observation_digest":"sha256:184ada90449abdc5c61a47ea324002e97ac2db309c66f732e8c443946fb14875","observation_id":"fa239f33-c0e3-4909-84fa-501e5a5f04fe","resolution":{"observed_at":"2026-08-10T22:48:43.922760Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T22:48:43.900458Z","title":"Side-channel attacks based on multi-loss regularized denoising autoencoder,","venue":null,"work_id":"f43dba58-e860-49b6-8414-71a05919f6da","year":2024},"citing_paper":{"arxiv_id":"2501.00824","last_updated":"2025-06-20T14:59:56Z","snapshot_observed_at":"2026-08-11T21:13:43.994902Z","submitted_at":"2025-01-01T13:00:01Z","title":"How Breakable Is Privacy: Probing and Resisting Model Inversion Attacks in Collaborative Inference","version":7},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-10T22:48:42.632799Z"},"links":{"citing_paper":"/paper/2501.00824"},"observation_digest":"sha256:10ba4f4cd57b313a8d2c1fe264748a70c92a8c4e2be859d8936660cdaaeb8dae","observation_id":"eb62aae9-004e-49b8-9a4f-906d8738d918","resolution":{"observed_at":"2026-08-10T22:48:43.905951Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T22:48:43.880890Z","title":"Mutual information neural estimation,","venue":null,"work_id":"44bab9c6-f322-4bbf-a71d-10b18852f949","year":2018},"citing_paper":{"arxiv_id":"2501.00824","last_updated":"2025-06-20T14:59:56Z","snapshot_observed_at":"2026-08-11T21:13:43.994902Z","submitted_at":"2025-01-01T13:00:01Z","title":"How Breakable Is Privacy: Probing and Resisting Model Inversion Attacks in Collaborative Inference","version":7},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-10T22:48:42.638268Z"},"links":{"citing_paper":"/paper/2501.00824"},"observation_digest":"sha256:2e4149a0a6bc91e526a4cd51e0f399038a4e9812c8e9d16bee6d8152f01edae2","observation_id":"254f7bff-595e-4454-a6a5-1a825e4b812e","resolution":{"observed_at":"2026-08-10T22:48:43.886233Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T22:48:42.644177Z","title":"Squeeze-and-excitation networks,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2501.00824","last_updated":"2025-06-20T14:59:56Z","snapshot_observed_at":"2026-08-11T21:13:43.994902Z","submitted_at":"2025-01-01T13:00:01Z","title":"How Breakable Is Privacy: Probing and Resisting Model Inversion Attacks in Collaborative Inference","version":7},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-10T22:48:42.644177Z"},"links":{"citing_paper":"/paper/2501.00824"},"observation_digest":"sha256:3f8d091ad7ccd8e055297b6f8341edcbdbbf5ca722afee529dbec6fd38e7625d","observation_id":"a20582c8-7d3c-487f-8c79-2f01e536bbf6","resolution":{"observed_at":"2026-08-10T22:48:42.644177Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T22:48:43.851664Z","title":"Rotate to attend: Convolutional triplet attention module,","venue":null,"work_id":"8756e218-3040-4e7c-b175-78be1dfb9bdb","year":2021},"citing_paper":{"arxiv_id":"2501.00824","last_updated":"2025-06-20T14:59:56Z","snapshot_observed_at":"2026-08-11T21:13:43.994902Z","submitted_at":"2025-01-01T13:00:01Z","title":"How Breakable Is Privacy: Probing and Resisting Model Inversion Attacks in Collaborative Inference","version":7},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-10T22:48:42.649479Z"},"links":{"citing_paper":"/paper/2501.00824"},"observation_digest":"sha256:2070a642ac296e455d80d05f12c25e01421bb7f50479e9635e602eebd044a06e","observation_id":"67fb82e3-c9ee-4d37-88ba-4839a5bd3d80","resolution":{"observed_at":"2026-08-10T22:48:43.857209Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T22:48:43.832855Z","title":"Cbam: Convolutional block attention module,","venue":null,"work_id":"f1dbe3ce-d6a1-4282-9603-c84837386116","year":2018},"citing_paper":{"arxiv_id":"2501.00824","last_updated":"2025-06-20T14:59:56Z","snapshot_observed_at":"2026-08-11T21:13:43.994902Z","submitted_at":"2025-01-01T13:00:01Z","title":"How Breakable Is Privacy: Probing and Resisting Model Inversion Attacks in Collaborative Inference","version":7},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-10T22:48:42.655032Z"},"links":{"citing_paper":"/paper/2501.00824"},"observation_digest":"sha256:96e9a184b8a1f4bedeb7cde2d1c3617621f0df24e4242620157dfd16a22d4463","observation_id":"c69a58f0-0940-4e39-ac20-d4e6b98d0040","resolution":{"observed_at":"2026-08-10T22:48:43.838530Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.10483","last_updated":"2025-03-21T22:27:01Z","snapshot_observed_at":"2026-07-06T16:33:55.369704Z","submitted_at":"2023-10-16T15:03:55Z","title":"Passive Inference Attacks on Split Learning via Adversarial Regularization","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.10483","snapshot_observed_at":"2026-08-10T22:48:42.660550Z","title":"Passive inference attacks on split learn- ing via adversarial regularization,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.00824","last_updated":"2025-06-20T14:59:56Z","snapshot_observed_at":"2026-08-11T21:13:43.994902Z","submitted_at":"2025-01-01T13:00:01Z","title":"How Breakable Is Privacy: Probing and Resisting Model Inversion Attacks in Collaborative Inference","version":7},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-10T22:48:42.660550Z"},"links":{"cited_paper":"/paper/2310.10483","citing_paper":"/paper/2501.00824"},"observation_digest":"sha256:7152c22c820575f258d9d95edc4ab8a77cbbd9199d65ea844fb0cbcde806a702","observation_id":"fb2385bc-b1f2-4eb1-a003-1c1eb0af8ca3","resolution":{"observed_at":"2026-08-10T22:48:42.660550Z","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":"2026-08-10T22:48:42.666494Z","title":"Model inversion attacks that exploit confidence information and basic countermeasures,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2501.00824","last_updated":"2025-06-20T14:59:56Z","snapshot_observed_at":"2026-08-11T21:13:43.994902Z","submitted_at":"2025-01-01T13:00:01Z","title":"How Breakable Is Privacy: Probing and Resisting Model Inversion Attacks in Collaborative Inference","version":7},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-10T22:48:42.666494Z"},"links":{"citing_paper":"/paper/2501.00824"},"observation_digest":"sha256:5bf2c95bc3882af522a0abb80d13d58bcbfbe89633c12db0a371096e68f3e7b3","observation_id":"a720b835-6c23-4aff-9280-fbe7d0e63a9e","resolution":{"observed_at":"2026-08-10T22:48:42.666494Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T22:48:43.803423Z","title":"Nonlinear total variation based noise removal algorithms,","venue":null,"work_id":"3435bff2-6a4d-4764-8736-07d8f4c835d6","year":1992},"citing_paper":{"arxiv_id":"2501.00824","last_updated":"2025-06-20T14:59:56Z","snapshot_observed_at":"2026-08-11T21:13:43.994902Z","submitted_at":"2025-01-01T13:00:01Z","title":"How Breakable Is Privacy: Probing and Resisting Model Inversion Attacks in Collaborative Inference","version":7},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-10T22:48:42.672120Z"},"links":{"citing_paper":"/paper/2501.00824"},"observation_digest":"sha256:3009814ab7b24a20e484138dc675524285193230fadccaca524f8d9085743bb9","observation_id":"46f302fb-90e3-45a7-8eaa-3d015f35a9cf","resolution":{"observed_at":"2026-08-10T22:48:43.808640Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T22:48:43.785983Z","title":"Analysis and utilization of hidden information in model inversion attacks,","venue":null,"work_id":"ad1f090c-1278-4f76-8bfd-ae126a39a89c","year":2023},"citing_paper":{"arxiv_id":"2501.00824","last_updated":"2025-06-20T14:59:56Z","snapshot_observed_at":"2026-08-11T21:13:43.994902Z","submitted_at":"2025-01-01T13:00:01Z","title":"How Breakable Is Privacy: Probing and Resisting Model Inversion Attacks in Collaborative Inference","version":7},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-10T22:48:42.677275Z"},"links":{"citing_paper":"/paper/2501.00824"},"observation_digest":"sha256:82dd9700aaf53a4d190e628e93e7bd5c140c6f063e3a8b461fdba4a30ad4b8a5","observation_id":"74b13eaa-a361-474c-ae75-ef18b549f4cb","resolution":{"observed_at":"2026-08-10T22:48:43.791360Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T22:48:43.768945Z","title":"Medical image denoising using convolutional denoising autoencoders,","venue":null,"work_id":"ef26f553-d7da-49bb-923b-0bfacda3f90c","year":2016},"citing_paper":{"arxiv_id":"2501.00824","last_updated":"2025-06-20T14:59:56Z","snapshot_observed_at":"2026-08-11T21:13:43.994902Z","submitted_at":"2025-01-01T13:00:01Z","title":"How Breakable Is Privacy: Probing and Resisting Model Inversion Attacks in Collaborative Inference","version":7},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-10T22:48:42.683172Z"},"links":{"citing_paper":"/paper/2501.00824"},"observation_digest":"sha256:331782ef3942337a4d4fc7d5f81487efa3b1d6fd8095d3bd06a9c9ad1bf3b1d4","observation_id":"dd18e0c9-1095-42c4-bb43-91b5e788c831","resolution":{"observed_at":"2026-08-10T22:48:43.774213Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.06549","last_updated":"2024-07-08T12:05:50Z","snapshot_observed_at":"2026-07-06T16:30:29.783501Z","submitted_at":"2023-10-10T11:51:12Z","title":"Be Careful What You Smooth For: Label Smoothing Can Be a Privacy Shield but Also a Catalyst for Model Inversion Attacks","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.06549","snapshot_observed_at":"2026-08-10T22:48:42.770842Z","title":"Be careful what you smooth for: Label smoothing can be a privacy shield but also a cat- alyst for model inversion attacks,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.00824","last_updated":"2025-06-20T14:59:56Z","snapshot_observed_at":"2026-08-11T21:13:43.994902Z","submitted_at":"2025-01-01T13:00:01Z","title":"How Breakable Is Privacy: Probing and Resisting Model Inversion Attacks in Collaborative Inference","version":7},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-10T22:48:42.770842Z"},"links":{"cited_paper":"/paper/2310.06549","citing_paper":"/paper/2501.00824"},"observation_digest":"sha256:06067c18671127da145d768507db7cc549620bea170e8e9d3746f712a546bdfe","observation_id":"0e62e35e-f764-4efe-96e0-8aa6638498f1","resolution":{"observed_at":"2026-08-10T22:48:42.770842Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.07973","last_updated":"2023-05-17T20:15:26Z","snapshot_observed_at":"2026-07-06T15:42:10.592303Z","submitted_at":"2023-05-17T20:15:26Z","title":"PrivaScissors: Enhance the Privacy of Collaborative Inference through the Lens of Mutual Information","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.07973","snapshot_observed_at":"2026-08-10T22:48:42.850488Z","title":"Privascissors: Enhance the privacy of collaborative inference through the lens of mutual information,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.00824","last_updated":"2025-06-20T14:59:56Z","snapshot_observed_at":"2026-08-11T21:13:43.994902Z","submitted_at":"2025-01-01T13:00:01Z","title":"How Breakable Is Privacy: Probing and Resisting Model Inversion Attacks in Collaborative Inference","version":7},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-10T22:48:42.850488Z"},"links":{"cited_paper":"/paper/2306.07973","citing_paper":"/paper/2501.00824"},"observation_digest":"sha256:13addf23e8b01ee314b48da82c81b632b5797cb7d4a59ae4b01ac5ffd0fdec7c","observation_id":"9890e370-2164-4071-b56a-48bef73f24cc","resolution":{"observed_at":"2026-08-10T22:48:42.850488Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T22:48:43.752346Z","title":"Club: A contrastive log-ratio upper bound of mutual information,","venue":null,"work_id":"14515207-eb8e-4f57-a508-3064c4585eb8","year":2020},"citing_paper":{"arxiv_id":"2501.00824","last_updated":"2025-06-20T14:59:56Z","snapshot_observed_at":"2026-08-11T21:13:43.994902Z","submitted_at":"2025-01-01T13:00:01Z","title":"How Breakable Is Privacy: Probing and Resisting Model Inversion Attacks in Collaborative Inference","version":7},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-10T22:48:42.911837Z"},"links":{"citing_paper":"/paper/2501.00824"},"observation_digest":"sha256:51859ea7dbbf33ea62bb8baeb29d73e730c65343b25df4170f662a49b0177cb1","observation_id":"ad8949e0-9dbc-4046-836a-94758671f882","resolution":{"observed_at":"2026-08-10T22:48:43.757934Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1901.04684","last_updated":"2019-01-15T07:21:44Z","snapshot_observed_at":"2026-07-06T07:26:45.900273Z","submitted_at":"2019-01-15T07:21:44Z","title":"The Limitations of Adversarial Training and the Blind-Spot Attack","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1901.04684","snapshot_observed_at":"2026-08-10T22:48:42.984470Z","title":"The limitations of adversarial training and the blind-spot attack,","venue":null,"work_id":null,"year":1901},"citing_paper":{"arxiv_id":"2501.00824","last_updated":"2025-06-20T14:59:56Z","snapshot_observed_at":"2026-08-11T21:13:43.994902Z","submitted_at":"2025-01-01T13:00:01Z","title":"How Breakable Is Privacy: Probing and Resisting Model Inversion Attacks in Collaborative Inference","version":7},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-10T22:48:42.984470Z"},"links":{"cited_paper":"/paper/1901.04684","citing_paper":"/paper/2501.00824"},"observation_digest":"sha256:26582a05bbd19bab88878280b93e04ae9e8413686166c41557ef09735e92bdb0","observation_id":"ac096976-bfb2-44f7-ac3a-1ea2984975c5","resolution":{"observed_at":"2026-08-10T22:48:42.984470Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T22:48:43.735253Z","title":"{FaceObfuscator}: Defending deep learning-based privacy attacks with gradient descent-resistant features in face recognition,","venue":null,"work_id":"2bf8a8df-c26a-4621-a451-2a7e6568e2d1","year":2024},"citing_paper":{"arxiv_id":"2501.00824","last_updated":"2025-06-20T14:59:56Z","snapshot_observed_at":"2026-08-11T21:13:43.994902Z","submitted_at":"2025-01-01T13:00:01Z","title":"How Breakable Is Privacy: Probing and Resisting Model Inversion Attacks in Collaborative Inference","version":7},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-10T22:48:42.990518Z"},"links":{"citing_paper":"/paper/2501.00824"},"observation_digest":"sha256:fc08ca37f26d73fb9941b05b61adf0df22432764a080747015183b728f389433","observation_id":"3a71759c-ba4f-4423-a6e1-0f28c48284d3","resolution":{"observed_at":"2026-08-10T22:48:43.740822Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T22:48:43.718060Z","title":"Deep residual learning for image recognition,","venue":null,"work_id":"e959a9ef-3a13-4a8f-8f05-5035a6ef71a5","year":2016},"citing_paper":{"arxiv_id":"2501.00824","last_updated":"2025-06-20T14:59:56Z","snapshot_observed_at":"2026-08-11T21:13:43.994902Z","submitted_at":"2025-01-01T13:00:01Z","title":"How Breakable Is Privacy: Probing and Resisting Model Inversion Attacks in Collaborative Inference","version":7},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-10T22:48:42.998522Z"},"links":{"citing_paper":"/paper/2501.00824"},"observation_digest":"sha256:6d7d6b5b9319606edb6728e734b3b6b1e23c5d29919b83489f3da9e084266447","observation_id":"61a88d00-b33e-4310-a4e6-2cdce93cacaa","resolution":{"observed_at":"2026-08-10T22:48:43.723629Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T22:48:43.700684Z","title":"Sok: Model inversion attack landscape: Taxonomy, chal- lenges, and future roadmap,","venue":null,"work_id":"5d0e5422-11b6-4d9c-9092-f46f3677241b","year":2023},"citing_paper":{"arxiv_id":"2501.00824","last_updated":"2025-06-20T14:59:56Z","snapshot_observed_at":"2026-08-11T21:13:43.994902Z","submitted_at":"2025-01-01T13:00:01Z","title":"How Breakable Is Privacy: Probing and Resisting Model Inversion Attacks in Collaborative Inference","version":7},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-10T22:48:43.004569Z"},"links":{"citing_paper":"/paper/2501.00824"},"observation_digest":"sha256:c35e6f91314fc58f33a56aab4c7b78892e8c303a7f44d839cbfc4e6a3e86c246","observation_id":"3d331df8-5dd7-4b03-9826-1e0d338c3a7a","resolution":{"observed_at":"2026-08-10T22:48:43.706184Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2209.10505","last_updated":"2022-09-21T17:05:12Z","snapshot_observed_at":"2026-07-06T13:54:49.290065Z","submitted_at":"2022-09-21T17:05:12Z","title":"Text Revealer: Private Text Reconstruction via Model Inversion Attacks against Transformers","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2209.10505","snapshot_observed_at":"2026-08-10T22:48:43.009486Z","title":"Text revealer: Private text reconstruction via model inversion attacks against transformers,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.00824","last_updated":"2025-06-20T14:59:56Z","snapshot_observed_at":"2026-08-11T21:13:43.994902Z","submitted_at":"2025-01-01T13:00:01Z","title":"How Breakable Is Privacy: Probing and Resisting Model Inversion Attacks in Collaborative Inference","version":7},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-10T22:48:43.009486Z"},"links":{"cited_paper":"/paper/2209.10505","citing_paper":"/paper/2501.00824"},"observation_digest":"sha256:d2b90627e4c26d31baffdce209efbc69dcdda41a107d59a9d6ce402514e07a15","observation_id":"c9ff0232-fa8a-43a3-a365-899dc1523236","resolution":{"observed_at":"2026-08-10T22:48:43.009486Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T22:48:43.683447Z","title":"Pseudo label-guided model in- version attack via conditional generative adversarial network,","venue":null,"work_id":"3fd20507-85b5-4c77-863c-44a1b2ce615a","year":2023},"citing_paper":{"arxiv_id":"2501.00824","last_updated":"2025-06-20T14:59:56Z","snapshot_observed_at":"2026-08-11T21:13:43.994902Z","submitted_at":"2025-01-01T13:00:01Z","title":"How Breakable Is Privacy: Probing and Resisting Model Inversion Attacks in Collaborative Inference","version":7},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-10T22:48:43.015576Z"},"links":{"citing_paper":"/paper/2501.00824"},"observation_digest":"sha256:53e0d22fdb2fb4973b1d12fafa33c4b4c401357ff407438e704434041e14afed","observation_id":"5511382f-56af-410a-be02-2dc2b893dfe5","resolution":{"observed_at":"2026-08-10T22:48:43.689270Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T22:48:43.666960Z","title":"Query-efficient model inversion attacks: An information flow view,","venue":null,"work_id":"1b062b14-209a-4ec6-aa9d-f898bbdfbcfa","year":2025},"citing_paper":{"arxiv_id":"2501.00824","last_updated":"2025-06-20T14:59:56Z","snapshot_observed_at":"2026-08-11T21:13:43.994902Z","submitted_at":"2025-01-01T13:00:01Z","title":"How Breakable Is Privacy: Probing and Resisting Model Inversion Attacks in Collaborative Inference","version":7},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-10T22:48:43.020914Z"},"links":{"citing_paper":"/paper/2501.00824"},"observation_digest":"sha256:84991ea12c15be1a17b5a2042293934ce561fdb14e5b0c1e9fcfed103ef49941","observation_id":"1f6a6fb5-cae1-4fd4-98ee-39a6d4406482","resolution":{"observed_at":"2026-08-10T22:48:43.671775Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T22:48:43.651346Z","title":"Classificatory notes on the production and transmis- sion of technological knowledge,","venue":null,"work_id":"4fb3dc64-9477-44ca-96e3-7e24b80a7fc4","year":1969},"citing_paper":{"arxiv_id":"2501.00824","last_updated":"2025-06-20T14:59:56Z","snapshot_observed_at":"2026-08-11T21:13:43.994902Z","submitted_at":"2025-01-01T13:00:01Z","title":"How Breakable Is Privacy: Probing and Resisting Model Inversion Attacks in Collaborative Inference","version":7},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-10T22:48:43.026430Z"},"links":{"citing_paper":"/paper/2501.00824"},"observation_digest":"sha256:b36054581b4c86c1ee8f2c18b05ed0de83d019fbbde69d7727d0e56212e62895","observation_id":"2e924db0-e957-4031-9759-27f0c8454643","resolution":{"observed_at":"2026-08-10T22:48:43.656009Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T22:48:43.634264Z","title":"On the vulnerability of skip connections to model inversion attacks,","venue":null,"work_id":"ffd34d6f-81bb-42bb-b4a2-b3819bd9b5d6","year":2025},"citing_paper":{"arxiv_id":"2501.00824","last_updated":"2025-06-20T14:59:56Z","snapshot_observed_at":"2026-08-11T21:13:43.994902Z","submitted_at":"2025-01-01T13:00:01Z","title":"How Breakable Is Privacy: Probing and Resisting Model Inversion Attacks in Collaborative Inference","version":7},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-10T22:48:43.033725Z"},"links":{"citing_paper":"/paper/2501.00824"},"observation_digest":"sha256:46dfaf847bdcedca8dee7ccc631e0536a40003fe5e589bbc2acdc87880a57169","observation_id":"ba80a915-b38a-41a6-9259-800316cab1bc","resolution":{"observed_at":"2026-08-10T22:48:43.640670Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T22:48:43.616109Z","title":"Asymptotic evaluation of certain markov process expectations for large time. iv,","venue":null,"work_id":"fabe5f30-dbb0-4697-8457-57d3632f24ac","year":1983},"citing_paper":{"arxiv_id":"2501.00824","last_updated":"2025-06-20T14:59:56Z","snapshot_observed_at":"2026-08-11T21:13:43.994902Z","submitted_at":"2025-01-01T13:00:01Z","title":"How Breakable Is Privacy: Probing and Resisting Model Inversion Attacks in Collaborative Inference","version":7},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-10T22:48:43.039414Z"},"links":{"citing_paper":"/paper/2501.00824"},"observation_digest":"sha256:9a60320a0bcd3289dc10831029a8705943ecfefc859a226f5d7a9b349b273124","observation_id":"8041be33-66fe-4d16-9d11-241b285da920","resolution":{"observed_at":"2026-08-10T22:48:43.622349Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T22:48:43.598798Z","title":"Learning multiple layers of features from tiny images,","venue":null,"work_id":"81ee7054-a92a-40f4-b45a-8438bd859436","year":2009},"citing_paper":{"arxiv_id":"2501.00824","last_updated":"2025-06-20T14:59:56Z","snapshot_observed_at":"2026-08-11T21:13:43.994902Z","submitted_at":"2025-01-01T13:00:01Z","title":"How Breakable Is Privacy: Probing and Resisting Model Inversion Attacks in Collaborative Inference","version":7},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-10T22:48:43.044817Z"},"links":{"citing_paper":"/paper/2501.00824"},"observation_digest":"sha256:ada2f86a64f36aff53d9817b7f75f98d2c36ea7110abdaa1080b23d1b0107bfa","observation_id":"2fbd4625-ee99-4e81-a367-20f807a0942c","resolution":{"observed_at":"2026-08-10T22:48:43.604513Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T22:48:43.581907Z","title":"Feature screening via distance corre- lation learning,","venue":null,"work_id":"26561760-70c3-4e61-9bcb-3ab5b573da2d","year":2012},"citing_paper":{"arxiv_id":"2501.00824","last_updated":"2025-06-20T14:59:56Z","snapshot_observed_at":"2026-08-11T21:13:43.994902Z","submitted_at":"2025-01-01T13:00:01Z","title":"How Breakable Is Privacy: Probing and Resisting Model Inversion Attacks in Collaborative Inference","version":7},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-10T22:48:43.082293Z"},"links":{"citing_paper":"/paper/2501.00824"},"observation_digest":"sha256:020f1f0631559377b531d1b9567c3b0770c7a74c736b0ab78062aff5fd653636","observation_id":"dafe771b-e54e-48e5-b14f-2a4c0db06f16","resolution":{"observed_at":"2026-08-10T22:48:43.586759Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T22:48:43.565859Z","title":"Pearson correlation coefficient,","venue":null,"work_id":"6c8f326e-2b30-4356-84ff-ad2e5948e4c8","year":2009},"citing_paper":{"arxiv_id":"2501.00824","last_updated":"2025-06-20T14:59:56Z","snapshot_observed_at":"2026-08-11T21:13:43.994902Z","submitted_at":"2025-01-01T13:00:01Z","title":"How Breakable Is Privacy: Probing and Resisting Model Inversion Attacks in Collaborative Inference","version":7},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-10T22:48:43.117819Z"},"links":{"citing_paper":"/paper/2501.00824"},"observation_digest":"sha256:a26fa4c8766f8d81d1c220bba631e9e9375d8d65ab390486885c0bbeee2031b3","observation_id":"ff4606d0-3e29-4c66-8291-baff5bb242f1","resolution":{"observed_at":"2026-08-10T22:48:43.570836Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T22:48:43.547779Z","title":"Model inversion robust- ness: Can transfer learning help?","venue":null,"work_id":"a9ed10cc-9342-4981-b14c-be2da56f1e11","year":2024},"citing_paper":{"arxiv_id":"2501.00824","last_updated":"2025-06-20T14:59:56Z","snapshot_observed_at":"2026-08-11T21:13:43.994902Z","submitted_at":"2025-01-01T13:00:01Z","title":"How Breakable Is Privacy: Probing and Resisting Model Inversion Attacks in Collaborative Inference","version":7},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-10T22:48:43.122995Z"},"links":{"citing_paper":"/paper/2501.00824"},"observation_digest":"sha256:1d44d12f8e703c9a7e034e6ee3807bd0d19b80b611c1165e71563dc3349ee8c0","observation_id":"e304cb8e-1aa5-491b-b05a-b636d2f44b4f","resolution":{"observed_at":"2026-08-10T22:48:43.553760Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T22:48:43.530049Z","title":"Fisher information and stochastic complexity,","venue":null,"work_id":"8fa4941a-d9ea-4e24-aceb-84c3ede249ab","year":1996},"citing_paper":{"arxiv_id":"2501.00824","last_updated":"2025-06-20T14:59:56Z","snapshot_observed_at":"2026-08-11T21:13:43.994902Z","submitted_at":"2025-01-01T13:00:01Z","title":"How Breakable Is Privacy: Probing and Resisting Model Inversion Attacks in Collaborative Inference","version":7},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-10T22:48:43.128392Z"},"links":{"citing_paper":"/paper/2501.00824"},"observation_digest":"sha256:bc240aa00b7ac4ff2a9728a78b82540331c601a304fdd54c19efb5e9f010754f","observation_id":"86929a9b-751f-4a2d-b8c5-fe54ff888e39","resolution":{"observed_at":"2026-08-10T22:48:43.535484Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T22:48:43.511321Z","title":"Inception-v4, inception- resnet and the impact of residual connections on learning,","venue":null,"work_id":"d3894e1f-671f-4f7a-976f-4222ef093d83","year":2017},"citing_paper":{"arxiv_id":"2501.00824","last_updated":"2025-06-20T14:59:56Z","snapshot_observed_at":"2026-08-11T21:13:43.994902Z","submitted_at":"2025-01-01T13:00:01Z","title":"How Breakable Is Privacy: Probing and Resisting Model Inversion Attacks in Collaborative Inference","version":7},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-10T22:48:43.133345Z"},"links":{"citing_paper":"/paper/2501.00824"},"observation_digest":"sha256:54e622abd925edf84d86da965d1f4e650523c42e7b4ea5c630eb271aa59aef2f","observation_id":"de73955f-1733-4cab-8e4b-1a4a3562fb6d","resolution":{"observed_at":"2026-08-10T22:48:43.517038Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T22:48:43.493810Z","title":"Kernel methods for measuring indepen- dence,","venue":null,"work_id":"5d3778c2-98b5-4c9e-a5c1-c0db671c2b33","year":2005},"citing_paper":{"arxiv_id":"2501.00824","last_updated":"2025-06-20T14:59:56Z","snapshot_observed_at":"2026-08-11T21:13:43.994902Z","submitted_at":"2025-01-01T13:00:01Z","title":"How Breakable Is Privacy: Probing and Resisting Model Inversion Attacks in Collaborative Inference","version":7},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-10T22:48:43.138941Z"},"links":{"citing_paper":"/paper/2501.00824"},"observation_digest":"sha256:e95786728640d23779f239403a22c274d60adcf5c99d3270320315c0fc1c52cb","observation_id":"4796522d-044a-4d4d-bb07-3106da1d7656","resolution":{"observed_at":"2026-08-10T22:48:43.499253Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T22:48:43.470674Z","title":"Plug & play attacks: Towards robust and flexible model inversion attacks,","venue":null,"work_id":"b7021b4b-b5a3-4138-8c4c-0a67e3cfad74","year":2022},"citing_paper":{"arxiv_id":"2501.00824","last_updated":"2025-06-20T14:59:56Z","snapshot_observed_at":"2026-08-11T21:13:43.994902Z","submitted_at":"2025-01-01T13:00:01Z","title":"How Breakable Is Privacy: Probing and Resisting Model Inversion Attacks in Collaborative Inference","version":7},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-10T22:48:43.144442Z"},"links":{"citing_paper":"/paper/2501.00824"},"observation_digest":"sha256:f0bdc6cb84fc4727f4bff3d8969765c94ddb9c9d3480bb30b54f7783498feb87","observation_id":"c0ac6a5c-e63c-4313-86a0-3f30eaa5f534","resolution":{"observed_at":"2026-08-10T22:48:43.481028Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T22:48:43.452688Z","title":"Measuring statistical de- pendence with hilbert-schmidt norms,","venue":null,"work_id":"12390212-dab4-4859-b5c2-9433892f584a","year":2005},"citing_paper":{"arxiv_id":"2501.00824","last_updated":"2025-06-20T14:59:56Z","snapshot_observed_at":"2026-08-11T21:13:43.994902Z","submitted_at":"2025-01-01T13:00:01Z","title":"How Breakable Is Privacy: Probing and Resisting Model Inversion Attacks in Collaborative Inference","version":7},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-10T22:48:43.150146Z"},"links":{"citing_paper":"/paper/2501.00824"},"observation_digest":"sha256:fd63bcd0ec5e633a156705f2070e17c819f2e3805caf4a67f60f80bd6484891b","observation_id":"531b0c36-d0fc-4ff2-9c97-ff1fc20ea26d","resolution":{"observed_at":"2026-08-10T22:48:43.458404Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T22:48:43.433305Z","title":"A data-driven approach to cleaning large face datasets,","venue":null,"work_id":"8b308401-e4e9-4574-a4ae-0ca859808ed6","year":2014},"citing_paper":{"arxiv_id":"2501.00824","last_updated":"2025-06-20T14:59:56Z","snapshot_observed_at":"2026-08-11T21:13:43.994902Z","submitted_at":"2025-01-01T13:00:01Z","title":"How Breakable Is Privacy: Probing and Resisting Model Inversion Attacks in Collaborative Inference","version":7},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-10T22:48:43.155781Z"},"links":{"citing_paper":"/paper/2501.00824"},"observation_digest":"sha256:f8e0eec2fd6df3934ace3bf9e03ae9e8feff37b601abf188cc22b614d4919656","observation_id":"82a37c23-598d-47d4-924d-02baf5ec1b5c","resolution":{"observed_at":"2026-08-10T22:48:43.439216Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T22:48:43.413083Z","title":"Deep learning face attributes in the wild,","venue":null,"work_id":"52d52c21-ee8f-4ab6-b249-06d5f272ada5","year":2015},"citing_paper":{"arxiv_id":"2501.00824","last_updated":"2025-06-20T14:59:56Z","snapshot_observed_at":"2026-08-11T21:13:43.994902Z","submitted_at":"2025-01-01T13:00:01Z","title":"How Breakable Is Privacy: Probing and Resisting Model Inversion Attacks in Collaborative Inference","version":7},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-10T22:48:43.162126Z"},"links":{"citing_paper":"/paper/2501.00824"},"observation_digest":"sha256:0368d39e408cfc26d440cea41528ca4703d8b81f6945f55e930b9010f77779ee","observation_id":"7c833ea4-0f4d-4f62-a86c-f7743ac8cff4","resolution":{"observed_at":"2026-08-10T22:48:43.419561Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T22:48:43.394143Z","title":"Curated dataset for covid-19 posterior-anterior chest radiography images (x-rays),","venue":null,"work_id":"077102f1-9f92-49bd-8cda-1de7858ca309","year":2020},"citing_paper":{"arxiv_id":"2501.00824","last_updated":"2025-06-20T14:59:56Z","snapshot_observed_at":"2026-08-11T21:13:43.994902Z","submitted_at":"2025-01-01T13:00:01Z","title":"How Breakable Is Privacy: Probing and Resisting Model Inversion Attacks in Collaborative Inference","version":7},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-10T22:48:43.168334Z"},"links":{"citing_paper":"/paper/2501.00824"},"observation_digest":"sha256:c3a52898dd4e81cd48e94b7d9027200e7571594c9ab592cd76a2df82750ded5c","observation_id":"f252451f-d8a1-4962-88f8-b14d4b0aca06","resolution":{"observed_at":"2026-08-10T22:48:43.400086Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1409.1556","last_updated":"2015-04-10T16:25:04Z","snapshot_observed_at":"2026-08-12T14:19:29.389332Z","submitted_at":"2014-09-04T19:48:04Z","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1409.1556","snapshot_observed_at":"2026-08-10T22:48:43.173915Z","title":"Very deep convolutional networks for large-scale image recognition,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2501.00824","last_updated":"2025-06-20T14:59:56Z","snapshot_observed_at":"2026-08-11T21:13:43.994902Z","submitted_at":"2025-01-01T13:00:01Z","title":"How Breakable Is Privacy: Probing and Resisting Model Inversion Attacks in Collaborative Inference","version":7},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-10T22:48:43.173915Z"},"links":{"cited_paper":"/paper/1409.1556","citing_paper":"/paper/2501.00824"},"observation_digest":"sha256:324c2fcb98886cd1769bcf173533ed5b4264438c7f8e80c713c8701b87ae7d36","observation_id":"4f9a31b1-d468-4ae9-845e-4ce8aa1e816b","resolution":{"observed_at":"2026-08-10T22:48:43.173915Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T22:48:43.370032Z","title":"Deep learning with differential privacy,","venue":null,"work_id":"cb4f85e6-9116-459e-9f1f-9f5b9f499a6d","year":2016},"citing_paper":{"arxiv_id":"2501.00824","last_updated":"2025-06-20T14:59:56Z","snapshot_observed_at":"2026-08-11T21:13:43.994902Z","submitted_at":"2025-01-01T13:00:01Z","title":"How Breakable Is Privacy: Probing and Resisting Model Inversion Attacks in Collaborative Inference","version":7},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-10T22:48:43.180083Z"},"links":{"citing_paper":"/paper/2501.00824"},"observation_digest":"sha256:1a11f3a904f36c3604cedd3355e58997f917b11c6f0ca9af0a2e920c185b6940","observation_id":"1ac3b6b1-4b42-4c65-9d6f-42593a3a6f2d","resolution":{"observed_at":"2026-08-10T22:48:43.377830Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2501.00824","last_updated":"2025-06-20T14:59:56Z","latest_version":7,"primary_category":"cs.CR","snapshot_observed_at":"2026-08-11T21:13:43.994902Z","submitted_at":"2025-01-01T13:00:01Z","title":"How Breakable Is Privacy: Probing and Resisting Model Inversion Attacks in Collaborative Inference"},"reference_resolution":{"displayed":59,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":13,"verified_exact":0,"verified_fuzzy":46},"total_outbound_references":59},"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":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"thesis":"As of 12 August 2026, this Paper Citation Record lists 59 of 59 outbound references and 0 inbound Pith citation observations for arXiv:2501.00824."}