{"as_of":"2026-08-13T09:26:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:2ce2c0c74a53acdbe6ac57be85c17decf67d1acf85adc0d46ced5d69d5fc55b3","coverage":[{"denominator":84,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":84,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T17:24:26.108033Z","state":"measured"},{"denominator":86,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":86,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-13T06:32:02.005865+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":"2026-07-14T17:36:18.728469Z","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":"2026-06-30T09:54:34.401614Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"cited_work":{"arxiv_id":"2412.08969","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2412.08969","snapshot_observed_at":"2026-06-30T09:54:34.401614Z","title":"Deep learning model security: Threats and defenses","venue":null,"work_id":"df213bb6-c309-4562-a940-a6f2a88b727f","year":null},"citing_paper":{"arxiv_id":"2606.28943","last_updated":"2026-06-27T14:30:43Z","snapshot_observed_at":"2026-07-31T16:02:13.460407Z","submitted_at":"2026-06-27T14:30:43Z","title":"A3M: Adaptive, Adversarial and Multi-Objective Learning for Strategic Bidding in Repeated Auctions","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-06-30T09:54:05.683478Z"},"links":{"cited_paper":"/paper/2412.08969","citing_paper":"/paper/2606.28943"},"observation_digest":"sha256:e3ae4a7915211b79c3e2ff047aaa8254383468b8124dcf977d4278ea89e2bfa6","observation_id":"f1a692df-d60d-413f-8506-cd31bd64a80b","resolution":{"observed_at":"2026-06-30T09:54:34.403192Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.08969","snapshot_observed_at":"2026-07-14T17:36:18.728469Z","title":"Deep learning model security: Threats and defenses","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.09695","last_updated":"2026-06-20T04:02:49Z","snapshot_observed_at":"2026-08-08T18:20:26.208499Z","submitted_at":"2026-06-20T04:02:49Z","title":"FedCausal-Dyn: A Causal-Dynamic Paradigm for Federated Learning under Dynamic Feature Drift","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-07-14T17:36:18.728469Z"},"links":{"cited_paper":"/paper/2412.08969","citing_paper":"/paper/2607.09695"},"observation_digest":"sha256:e151dc52207838261bc148625d7a7d604af88abf5037fbdccf2a0a06a370cd83","observation_id":"621cf58c-e0d6-42ea-81c3-d49222504b18","resolution":{"observed_at":"2026-07-14T17:36:18.728469Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2412.08969/citation-record","integrity":"/paper/2412.08969/integrity","json":"/paper/2412.08969/citation-record.json","paper":"/paper/2412.08969"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T17:24:25.579907Z","title":"Deep learning.nature, 521(7553):436–444, 2015","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:25.579907Z"},"links":{"citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:1d99caeb82dd4d48d101c9db35b61f32ca911135f1f45ff83938622f89e1be05","observation_id":"273ab71b-86fb-4aec-bef0-30766f9e2155","resolution":{"observed_at":"2026-08-11T17:24:25.579907Z","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":"2026-08-11T17:24:25.588417Z","title":"MIT Press, 2016","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:25.588417Z"},"links":{"citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:6140464e1f58047dd9244ccd6e3684e59afba729af713133c6de21bb3a862da5","observation_id":"c0905f6e-d753-4a66-ad17-8d64aae5f004","resolution":{"observed_at":"2026-08-11T17:24:25.588417Z","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":"2026-08-11T17:24:25.595377Z","title":"Deep learning , volume 1","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:25.595377Z"},"links":{"citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:883689666dd208135cc589fe416225e6c38f711c9ba39dfc334603b24dbb3598","observation_id":"7a522030-018c-4a7c-8904-4c7af03e3dd3","resolution":{"observed_at":"2026-08-11T17:24:25.595377Z","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":"2026-08-11T17:24:25.602833Z","title":"Atoms of recognition in human and computer vision","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:25.602833Z"},"links":{"citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:9f995cb09faea9531fb28db2b27e1adaba79bdfabc581c959d05811e706f2675","observation_id":"68974850-b6c9-49ed-9d12-7f66955e8c58","resolution":{"observed_at":"2026-08-11T17:24:25.602833Z","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":"2026-08-11T17:24:25.610812Z","title":"Understanding natural language","venue":null,"work_id":null,"year":1972},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:25.610812Z"},"links":{"citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:7bc639444ebc64631ac4286b25619fca7da0dfc195255d6be6371b0e00c46aa3","observation_id":"b5023a38-2e5b-41ec-b220-3d03faf11b11","resolution":{"observed_at":"2026-08-11T17:24:25.610812Z","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":"2026-08-11T17:24:28.177325Z","title":"Playing games","venue":null,"work_id":"cc7ee72a-88aa-4db1-91a0-f595cd3b29a3","year":2015},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:25.617813Z"},"links":{"citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:43a714d02e9bac03f7d9767f51f3cc1fd8b3acd9c89351a77144add080514cbe","observation_id":"8e731c4c-f7a4-4e6d-b88b-0ba45973cb19","resolution":{"observed_at":"2026-08-11T17:24:28.184170Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T17:24:28.157084Z","title":"An introduction to Python","venue":null,"work_id":"26f8b5be-8a25-4542-a952-175da9cdaa70","year":2003},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:25.630678Z"},"links":{"citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:5abc623944b050b7f9cc17b0202d890c0afa40328cb1b5557a256661bc16a84a","observation_id":"7339f096-c800-4900-b07e-11090898c4e7","resolution":{"observed_at":"2026-08-11T17:24:28.163277Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T17:24:25.648675Z","title":"Pytorch: An imperative style, high-performance deep learning library","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:25.648675Z"},"links":{"citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:0dcc9fc5a69f61ebff7f9198895341a17cfb6b1cb5841830a34a2beb8d35962c","observation_id":"503b16a4-5358-48db-b99b-d5dd1cf132e3","resolution":{"observed_at":"2026-08-11T17:24:25.648675Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1803.08375","last_updated":"2026-04-14T12:21:53Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2018-03-22T14:30:17Z","title":"Deep Learning using Rectified Linear Units (ReLU)","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1803.08375","snapshot_observed_at":"2026-08-11T17:24:25.655894Z","title":"Deep learning using rectified linear units (relu)","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:25.655894Z"},"links":{"cited_paper":"/paper/1803.08375","citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:e3f76372aae365a08f9f3e8c5a2c8ac18521e25f70c8a4cb0821f0b023fcad76","observation_id":"7dece865-78eb-4b45-bcc3-06b67b50d648","resolution":{"observed_at":"2026-08-11T17:24:25.655894Z","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":"2026-08-11T17:24:25.663084Z","title":"Stochastic gradient descent tricks","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:25.663084Z"},"links":{"citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:c08c71e0547d164be536d9131b5a1243b51f14f0eb924437d79c0d972755a3e4","observation_id":"2054e25f-325e-4424-9bae-28e130ed2acf","resolution":{"observed_at":"2026-08-11T17:24:25.663084Z","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":"2026-08-11T17:24:25.669130Z","title":"Deep learning and machine learning – object detection and semantic segmentation: From theory to applications","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:25.669130Z"},"links":{"citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:de7f6c1bac3f38fe071c522e6e426ac66638f7b54ad09b41a2783767e83f50f7","observation_id":"af731050-0fc1-4ed6-b2ff-4f4acf6fcf15","resolution":{"observed_at":"2026-08-11T17:24:25.669130Z","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":"2410.19849","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T17:24:27.062616Z","title":"Deep learning and machine learning – python data structures and math- ematics fundamental: From theory to practice","venue":null,"work_id":"d5985a93-af5f-4e5c-98b9-9195b30d4b58","year":null},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:25.675877Z"},"links":{"citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:739c881ca7526ac4015fa57927a2a277e7a7d40497c6195497e9ea5b56f47f17","observation_id":"4d58233f-8a6c-4f0f-8096-1be7f94cf8b0","resolution":{"observed_at":"2026-08-11T17:24:27.075119Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T17:24:28.113339Z","title":"Review on methods to fix number of hidden neurons in neural networks","venue":null,"work_id":"8d6f1fc2-b23a-4c25-bfd6-b3be01e1390e","year":2013},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:25.682659Z"},"links":{"citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:6be5e4bbc3a12a328670fbd51508a560a50efe3550a7e5fb8449ca73580da1ed","observation_id":"5101f9b6-03f0-457f-9987-5ac566aab3c4","resolution":{"observed_at":"2026-08-11T17:24:28.119600Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T17:24:28.094258Z","title":"The influence of the sigmoid function parameters on the speed of backpropagation learning","venue":null,"work_id":"028324e8-93d3-4b40-8c3c-808af24a331c","year":null},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:25.688940Z"},"links":{"citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:c5ef43b116082cd1d36fb2ac7ea36536be6852aaec3d3e26639b27926b5385f4","observation_id":"da368dad-d64b-4711-b329-7b3f8b115bdc","resolution":{"observed_at":"2026-08-11T17:24:28.099418Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T17:24:25.696111Z","title":"Learning both weights and connections for efficient neural network","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:25.696111Z"},"links":{"citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:7411c5175178220886181e75667c647fd4d3ec526a6a49338e00ef6be4d97c3c","observation_id":"b8e927df-5f0e-429e-8b06-058fe993ae78","resolution":{"observed_at":"2026-08-11T17:24:25.696111Z","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":"2410.20304","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T17:24:26.966576Z","title":"Deep learning, machine learning – digital signal and image processing: From theory to application","venue":null,"work_id":"b23f4cda-965e-47d1-b25c-c691baf76469","year":null},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:25.701311Z"},"links":{"citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:f2637f7339fa56bf00d963a7b6f5eb5adf2fe122940bce460e3559674456f1b9","observation_id":"1d6e27a4-4d0c-4daf-a160-33973d828ab4","resolution":{"observed_at":"2026-08-11T17:24:26.976174Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1702.02284","last_updated":"2017-02-08T04:33:55Z","snapshot_observed_at":"2026-08-13T07:00:50.216169Z","submitted_at":"2017-02-08T04:33:55Z","title":"Adversarial Attacks on Neural Network Policies","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1702.02284","snapshot_observed_at":"2026-08-11T17:24:25.707696Z","title":"Adversarial attacks on neural network policies","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:25.707696Z"},"links":{"cited_paper":"/paper/1702.02284","citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:f2ccc3f17781ace472c662ce0b8b9d59b757c3564b5464320329d152f5132091","observation_id":"40729590-7943-4ca8-bb6c-e28df75700b3","resolution":{"observed_at":"2026-08-11T17:24:25.707696Z","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":"2026-08-11T17:24:25.714213Z","title":"Certified defenses for data poisoning attacks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:25.714213Z"},"links":{"citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:216551675d7ba3c9e287c6a5dae0fd18d1e597ce41cb3e89ac3fd42e02e50e6a","observation_id":"34795f1a-f8ae-4346-9e3a-597130d2d469","resolution":{"observed_at":"2026-08-11T17:24:25.714213Z","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":"2026-08-11T17:24:28.044145Z","title":"Ensemble machine learning models for the detection of energy theft","venue":null,"work_id":"bdc2043a-5b50-48e5-b45e-483560e9dee5","year":2021},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:25.720685Z"},"links":{"citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:9c66efdcce5009aa159ec037f5a61a1c6a9914609dc659be1e9ee2102f1f5a40","observation_id":"e8bf3862-79dc-42a7-89e6-0718f36bceec","resolution":{"observed_at":"2026-08-11T17:24:28.058144Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2110.12734","last_updated":"2022-02-04T04:32:52Z","snapshot_observed_at":"2026-08-01T21:52:31.314382Z","submitted_at":"2021-10-25T08:46:00Z","title":"Fast Gradient Non-sign Methods","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.12734","snapshot_observed_at":"2026-08-11T17:24:25.726429Z","title":"Fast gradient non-sign methods","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:25.726429Z"},"links":{"cited_paper":"/paper/2110.12734","citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:82592da4cc23323a8031c0cf2c0f0bfefe52bcb0071fd6b8bc9e48ee0b55b0c6","observation_id":"d07015d5-3ac9-457d-9db8-40e5cc37199c","resolution":{"observed_at":"2026-08-11T17:24:25.726429Z","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":"2026-08-11T17:24:25.732079Z","title":"Model inversion attacks that exploit confidence information and basic countermeasures","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:25.732079Z"},"links":{"citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:3196434810784192cacd61ea7eb5e2c10bfa1dd8aa4b7f735058be0ebaca4d6e","observation_id":"5f7920c6-25e9-42fe-81ca-0323617b2557","resolution":{"observed_at":"2026-08-11T17:24:25.732079Z","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":"2026-08-11T17:24:28.012684Z","title":"A survey on data poisoning attacks and defenses","venue":null,"work_id":"6872036f-e407-4ec6-8cd3-8a754b2ef123","year":2022},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:25.737316Z"},"links":{"citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:e64bab835c867f264c4c467595671e8c1377355f2c23e9e323e39abc18e11c86","observation_id":"4e7735c7-e75d-4765-bdaf-3b6ac0a2d61c","resolution":{"observed_at":"2026-08-11T17:24:28.018405Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T17:24:27.993369Z","title":null,"venue":null,"work_id":"22c767ee-cfa3-4158-b3c4-6915644e4c21","year":2021},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:25.742690Z"},"links":{"citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:85320e3bd3d42af0197acc2db3f3e6a3bf62f3189dfed83cc5af1f68ae6e0956","observation_id":"1fb823dc-06d6-4f2f-9406-91ee58867cf4","resolution":{"observed_at":"2026-08-11T17:24:27.999235Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T17:24:25.748628Z","title":"Securing large language models: Addressing bias, misinformation, and prompt attacks","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:25.748628Z"},"links":{"citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:b07faa0906af30f242f05db5dd56088990540163199ce91465a935f010a9e2e7","observation_id":"56b5e1b4-cdf9-4e57-b58f-866865ff14ba","resolution":{"observed_at":"2026-08-11T17:24:25.748628Z","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":"2026-08-11T17:24:25.753855Z","title":"Deep learning and machine learning with gpgpu and cuda: Unlocking the power of parallel computing","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:25.753855Z"},"links":{"citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:9b7ecfd3308b9db713541e562f9efa42b120336af37b6abd875f5548cf9cdc66","observation_id":"0f5bbd3c-1c39-43fb-bdfe-219525c50bc7","resolution":{"observed_at":"2026-08-11T17:24:25.753855Z","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":"2410.01268","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T17:24:26.666622Z","title":"Deep learning and machine learning, advancing big data analytics and management: Unveiling BIBLIOGRAPHY 173 ai’s potential through tools, techniques, and applications","venue":null,"work_id":"fc6e2221-fefa-40c1-b99d-c838f91dc482","year":null},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:25.761444Z"},"links":{"citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:586bc3d248deb71265a65694b0bb9e5543f2ff698c188ce5925d67f27823c59e","observation_id":"47d77c40-28eb-4768-bab9-8339793332c3","resolution":{"observed_at":"2026-08-11T17:24:26.676831Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1708.07747","last_updated":"2017-09-15T21:29:49Z","snapshot_observed_at":"2026-07-06T05:56:41.814255Z","submitted_at":"2017-08-25T14:01:29Z","title":"Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1708.07747","snapshot_observed_at":"2026-08-11T17:24:25.767968Z","title":"Fashion-mnist: a novel image dataset for bench- marking machine learning algorithms","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:25.767968Z"},"links":{"cited_paper":"/paper/1708.07747","citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:f931250bfcb257ba5d34120914269897f80d3b5caead89b8a56c2b1778db655b","observation_id":"c082e244-37dd-40e3-bfb2-14770b0df89e","resolution":{"observed_at":"2026-08-11T17:24:25.767968Z","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":"2026-08-11T17:24:27.974578Z","title":"Deep learning based vulnerability detection: Are we there yet? IEEE Transactions on Software Engineering , 48(9):3280–3296, 2021","venue":null,"work_id":"41db6306-a668-4fbb-847f-c504812d7252","year":2021},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:25.774031Z"},"links":{"citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:f6de9fe95ae75f8f6ead0f2d075b8befbe75cfc80ce4c106bc821d4f2d806d10","observation_id":"fb098449-3e97-45b9-871f-e7240e3bd25f","resolution":{"observed_at":"2026-08-11T17:24:27.980933Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T17:24:27.954762Z","title":"An empirical study of deep learning models for vulnerability detection","venue":null,"work_id":"09546118-149f-4e3b-9d6a-dda929ae23f6","year":2023},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:25.779305Z"},"links":{"citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:addd8fedd775fdf9e2284a480e9e87e78ea3b05fea90ec3a38fb59a3f40729e2","observation_id":"0e24e5e2-395f-47ae-8bf0-0570423a637d","resolution":{"observed_at":"2026-08-11T17:24:27.961796Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T17:24:27.932037Z","title":"Shallow or deep? an empirical study on detecting vulnerabilities using deep learning","venue":null,"work_id":"e82305fc-bc49-471b-ae00-a10f58886965","year":2021},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:25.784358Z"},"links":{"citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:137dea3b7708b596b714bcd401eb95af347574468f281867b65c5c50ad15d490","observation_id":"3c49f5ee-7a92-48d2-b678-ceca6f9996d5","resolution":{"observed_at":"2026-08-11T17:24:27.939650Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1511.05122","last_updated":"2016-03-04T20:21:24Z","snapshot_observed_at":"2026-07-06T04:36:40.942807Z","submitted_at":"2015-11-16T20:48:20Z","title":"Adversarial Manipulation of Deep Representations","version":9},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1511.05122","snapshot_observed_at":"2026-08-11T17:24:25.789387Z","title":"Adversarial manipulation of deep representations","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:25.789387Z"},"links":{"cited_paper":"/paper/1511.05122","citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:b535d86cceb7f7aba6206acfa45d026d7f446c35f7be9204bdb5d753db3c3e30","observation_id":"3bf2ef94-5d59-458d-8c2b-4ac69254c585","resolution":{"observed_at":"2026-08-11T17:24:25.789387Z","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":"2026-08-11T17:24:27.897672Z","title":"A survey of the implementations of model inversion attacks","venue":null,"work_id":"1ba241e4-0a19-4efe-8881-1869146331ad","year":2022},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:25.794309Z"},"links":{"citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:df9eadb752f718a803a48adf98ff54f02d8df946c4f4acd4691636d3a567c4ec","observation_id":"829ba41f-ad99-4a8a-a82c-371ea706903e","resolution":{"observed_at":"2026-08-11T17:24:27.903631Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T17:24:27.878560Z","title":"Practical black-box attacks against machine learning","venue":null,"work_id":"26297777-622a-4c4e-a183-72489471dc19","year":2017},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:25.799023Z"},"links":{"citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:8fe4aee47ca3f2e608fbfabb7863b5455b63ef630be7705a1ba1a04efb60b6bd","observation_id":"8c78ac99-ba87-4048-80ab-92a56dfac646","resolution":{"observed_at":"2026-08-11T17:24:27.884788Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T17:24:27.859957Z","title":"Survey on white-box attacks and solutions","venue":null,"work_id":"d5fe6e7c-b9d0-4874-8b1a-341a92392a88","year":2018},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:25.803641Z"},"links":{"citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:685460eb7998653bc3461f042a060ccbb23897cef1139c8b357e71ef3d305c43","observation_id":"ce5e6294-e606-48f2-9d67-9ccf55bd8853","resolution":{"observed_at":"2026-08-11T17:24:27.865655Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T17:24:27.842463Z","title":"Query efficient black-box adversarial attack on deep neural networks","venue":null,"work_id":"54d47cd3-48bc-45de-9f6e-49479ebc2f57","year":2023},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:25.808818Z"},"links":{"citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:75ad7af347d6190486d60789c7b81719fc46af9531067ab58230158ebf072665","observation_id":"c512e49d-30f5-4251-8c49-9e899f8e0696","resolution":{"observed_at":"2026-08-11T17:24:27.847768Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1605.07277","last_updated":"2016-05-24T03:27:48Z","snapshot_observed_at":"2026-08-10T08:37:57.468792Z","submitted_at":"2016-05-24T03:27:48Z","title":"Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1605.07277","snapshot_observed_at":"2026-08-11T17:24:25.813902Z","title":"Transferability in machine learn- ing: from phenomena to black-box attacks using adversarial samples","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:25.813902Z"},"links":{"cited_paper":"/paper/1605.07277","citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:c7806c01320ac4691686a4ff7fde8f1f25a2236f822c954bedcdf6ce9147fd32","observation_id":"8d5b4400-f48c-4632-99f3-d233dafae769","resolution":{"observed_at":"2026-08-11T17:24:25.813902Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1810.12042","last_updated":"2019-03-12T08:13:30Z","snapshot_observed_at":"2026-08-10T07:12:23.932614Z","submitted_at":"2018-10-29T10:30:20Z","title":"Logit Pairing Methods Can Fool Gradient-Based Attacks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1810.12042","snapshot_observed_at":"2026-08-11T17:24:25.819455Z","title":"Logit pairing methods can fool gradient-based attacks","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:25.819455Z"},"links":{"cited_paper":"/paper/1810.12042","citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:d216269f5349dd240735701c1b052793a1cc3bc05ca521b069b66ea19c865f58","observation_id":"a9b746f6-55cc-48bf-a5d3-323fe8bbe083","resolution":{"observed_at":"2026-08-11T17:24:25.819455Z","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":"2026-08-11T17:24:27.825833Z","title":"Adversarial attacks and defenses against deep neural networks: a survey","venue":null,"work_id":"98b3a852-9264-44ed-a01f-11d89689033f","year":2018},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:25.826328Z"},"links":{"citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:95bf59a664704d78d1804aecbd053b93b7f4ff53a155f417be561411dab33a5d","observation_id":"3f8d1966-f219-4197-bfb5-236df05b4288","resolution":{"observed_at":"2026-08-11T17:24:27.830683Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1712.02494","last_updated":"2017-12-07T05:13:54Z","snapshot_observed_at":"2026-07-06T06:13:11.382074Z","submitted_at":"2017-12-07T05:13:54Z","title":"Adversarial Examples that Fool Detectors","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1712.02494","snapshot_observed_at":"2026-08-11T17:24:25.831734Z","title":"Adversarial examples that fool detectors.arXiv preprint arXiv:1712.02494, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:25.831734Z"},"links":{"cited_paper":"/paper/1712.02494","citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:fd47cb6bf0b6af31906a277e84d17293e74eea7ddcc54a89e70a592bd6785a50","observation_id":"a3442380-250e-497f-bde1-0f7589de9176","resolution":{"observed_at":"2026-08-11T17:24:25.831734Z","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":"2026-08-11T17:24:27.808899Z","title":"Hands-on machine learning on google cloud platform: Implementing smart and efficient analytics using cloud ml engine","venue":null,"work_id":"649841bd-f529-48d4-a7af-f1b9a9a9b378","year":2018},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:25.837585Z"},"links":{"citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:4e493d9811387969cfcaea8f9207fed64c6a739292c83bb5f7ba10249c64f327","observation_id":"0d5275fc-2749-41ab-b98f-3620cf9a68b3","resolution":{"observed_at":"2026-08-11T17:24:27.814292Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T17:24:27.792401Z","title":"Gpt understands, too","venue":null,"work_id":"e05b08ec-de55-4991-af6c-c09e7842acf8","year":2023},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:25.842655Z"},"links":{"citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:21b20ba0d2947cee4215f83f609870a9bf7557e1df21b6d3532d06c8c40475fc","observation_id":"decd9ee1-4cb0-4253-9c90-b7b51d303767","resolution":{"observed_at":"2026-08-11T17:24:27.797601Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T17:24:25.847801Z","title":"Recent advances in convolutional neural networks","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:25.847801Z"},"links":{"citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:ff9a18fe205df02dc388bd9af799ee3af68118f0b605963dfa71b6bca3ec8926","observation_id":"2c6f6955-0838-483c-ad5c-99b0158c1963","resolution":{"observed_at":"2026-08-11T17:24:25.847801Z","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":"2026-08-11T17:24:25.856066Z","title":"A comprehensive survey on poisoning attacks and countermeasures in machine learning","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:25.856066Z"},"links":{"citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:e0574d142a53cef538e7d3a6b7edfb639f9bf065ea5133e4fbfc901af8b61711","observation_id":"aa3d7271-a9ec-4dc5-88f2-3f640e50a5f3","resolution":{"observed_at":"2026-08-11T17:24:25.856066Z","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":"2026-08-11T17:24:27.740996Z","title":"Deep model poisoning attack on feder- ated learning","venue":null,"work_id":"8ba4bfbd-def6-4f05-8805-27ee75c03307","year":2021},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:25.861919Z"},"links":{"citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:59996368bdb33c907404832e5c86863cdff1f029f434bc645928d8ad6cb482dc","observation_id":"d983b998-7f96-45c2-9877-a67c0b7f0f5a","resolution":{"observed_at":"2026-08-11T17:24:27.746259Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T17:24:27.723083Z","title":"A huber loss minimization approach to byzantine ro- bust federated learning","venue":null,"work_id":"dc53a91b-8f70-44e9-9935-b0f3c5b2e703","year":2024},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:25.867408Z"},"links":{"citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:df9e281cbf13d3b8be8d8cb5f9ecfe5a51c981b2270aaeef40174c29276253d5","observation_id":"723b2ee5-11e1-4995-8048-7428c54945a1","resolution":{"observed_at":"2026-08-11T17:24:27.728845Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T17:24:27.702800Z","title":"Rethinking label flipping attack: From sample masking to sample thresholding","venue":null,"work_id":"b1733b3a-e522-4d6a-984d-7e9478adf574","year":2022},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:25.872896Z"},"links":{"citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:3bac4441c721b3d4e357960dc64887f793ddea4b1bd95052e8e81c0c23e2eba8","observation_id":"b8ae63de-1f52-4151-8909-226395feb95e","resolution":{"observed_at":"2026-08-11T17:24:27.708579Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T17:24:27.684944Z","title":"Adversarial learning targeting deep neural network classification: A comprehensive review of defenses against attacks","venue":null,"work_id":"efe3a6c7-a2a5-413f-be42-a220582dcdd3","year":2020},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:25.878343Z"},"links":{"citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:de29cc18efbeb9a22d1c387bc375b06d8402c84696ad2fd525b7f93686b3a9f4","observation_id":"3d18cd12-75e4-47b2-acad-6d3226df967e","resolution":{"observed_at":"2026-08-11T17:24:27.690556Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T17:24:27.666787Z","title":"Generative adversarial nets","venue":null,"work_id":"ebce5638-1f7f-4042-98e7-64ee2f3eb46a","year":2014},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:25.884339Z"},"links":{"citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:5568455bd69d0db8a8b93989540f101521db558a1a93b696bae01d4ff8e0ea4f","observation_id":"735da356-e070-4d22-9e9e-046039d21ca8","resolution":{"observed_at":"2026-08-11T17:24:27.672348Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1706.06083","last_updated":"2019-09-04T18:53:10Z","snapshot_observed_at":"2026-08-07T14:27:46.872660Z","submitted_at":"2017-06-19T17:53:11Z","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1706.06083","snapshot_observed_at":"2026-08-11T17:24:25.890469Z","title":"Towards deep learning models resistant to adversarial attacks.arXiv preprint arXiv:1706.06083, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:25.890469Z"},"links":{"cited_paper":"/paper/1706.06083","citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:a6edaa8aa55be3e84c8f144e748937f51bce1e949eac65f243e4da018963dfc3","observation_id":"b0388668-921f-4775-ac7f-ab6fb1959976","resolution":{"observed_at":"2026-08-11T17:24:25.890469Z","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":"2026-08-11T17:24:25.898738Z","title":"Towards evaluating the robustness of neural networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:25.898738Z"},"links":{"citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:2a11f7f2ded0567dab6a362edd93d62f16d79bd401fc39f13089bbeaa7d90d79","observation_id":"df52c534-156b-4a35-973d-a40642f8cb64","resolution":{"observed_at":"2026-08-11T17:24:25.898738Z","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":"2026-08-11T17:24:25.905020Z","title":"Reflections on trusting trust","venue":null,"work_id":null,"year":1984},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:25.905020Z"},"links":{"citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:eec4c0e626081c41e69afb2b0de3392c6586137838705721a92a0465f241a7d8","observation_id":"a95f040f-6848-413d-9d3d-cfd8422a3a09","resolution":{"observed_at":"2026-08-11T17:24:25.905020Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1708.06733","last_updated":"2019-03-11T20:45:33Z","snapshot_observed_at":"2026-08-12T15:43:59.037380Z","submitted_at":"2017-08-22T17:31:54Z","title":"BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1708.06733","snapshot_observed_at":"2026-08-11T17:24:25.910669Z","title":"Badnets: Identifying vulnerabilities in the machine learning model supply chain","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:25.910669Z"},"links":{"cited_paper":"/paper/1708.06733","citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:a1a9eca7d6c3a0aff4e04464f5f3e415155361fc5cbf727136d9b22a439fa788","observation_id":"55f7a838-fd33-48a9-a59d-cbfaa2abce7b","resolution":{"observed_at":"2026-08-11T17:24:25.910669Z","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":"2026-08-11T17:24:27.620958Z","title":"An assessment by the statin intolerance panel: 2014 update","venue":null,"work_id":"580d92d5-0567-4a9d-b36a-0cecc3353c2d","year":2014},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:25.916413Z"},"links":{"citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:47cb7bd207aa3c2e851245ba748393adcf19d809e4c93f4dbc7177a8645881c6","observation_id":"5cea5925-2e2a-417d-baff-ea89ae3cb428","resolution":{"observed_at":"2026-08-11T17:24:27.627572Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1412.6572","last_updated":"2015-03-20T20:19:16Z","snapshot_observed_at":"2026-08-12T17:13:46.394331Z","submitted_at":"2014-12-20T01:17:12Z","title":"Explaining and Harnessing Adversarial Examples","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.6572","snapshot_observed_at":"2026-08-11T17:24:25.921555Z","title":"Explaining and harnessing adver- sarial examples","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:25.921555Z"},"links":{"cited_paper":"/paper/1412.6572","citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:0a0f3740affee206e60256c5b5b1c863e1d2d8957d31592206a744c0734616f8","observation_id":"339cadad-fd56-4ab0-9087-270393b811d8","resolution":{"observed_at":"2026-08-11T17:24:25.921555Z","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":"2026-08-11T17:24:27.602089Z","title":"The limitations of deep learning in adversarial settings","venue":null,"work_id":"ea693ccd-78aa-429f-819b-2fc337176c22","year":2016},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:25.926970Z"},"links":{"citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:437ac9a2926a72b240a172ec5d8ec34acfc61d42a74a8c6f6bb661ddc04cac18","observation_id":"298a8811-3f3c-44c2-aeed-f8599ed2f346","resolution":{"observed_at":"2026-08-11T17:24:27.607780Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2202.10276","last_updated":"2022-02-22T07:20:43Z","snapshot_observed_at":"2026-08-11T17:55:56.895921Z","submitted_at":"2022-02-21T14:43:38Z","title":"Poisoning Attacks and Defenses on Artificial Intelligence: A Survey","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.10276","snapshot_observed_at":"2026-08-11T17:24:25.932602Z","title":"Poisoning attacks and defenses on artificial intelligence: A survey","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:25.932602Z"},"links":{"cited_paper":"/paper/2202.10276","citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:1148f2243e0e2583fa6cbc890390dc3638e304c0b51896840bd095c7f4ed2cb6","observation_id":"3ff2cddf-dabf-4f02-b9a3-8b7684fa710e","resolution":{"observed_at":"2026-08-11T17:24:25.932602Z","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":"2026-08-11T17:24:27.581674Z","title":"Robust nonparametric regression under poisoning attack","venue":null,"work_id":"2431d73b-0635-4a74-924b-a536d5258112","year":2024},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:25.938983Z"},"links":{"citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:72429282794b169cc6e8759873da4e609f475074f8cdd4a6a594cb37ac46325f","observation_id":"91d85854-0dec-4b64-87be-c9f58a9e2af5","resolution":{"observed_at":"2026-08-11T17:24:27.587985Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T17:24:27.562956Z","title":"Calibrating noise to sensitivity in private data analysis","venue":null,"work_id":"4049bd83-3930-402a-9371-ccd55a41ba11","year":2006},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:25.946415Z"},"links":{"citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:3c2992860407332f08bc70bf16bec242987d1f4bb0534930e75425a34435b4de","observation_id":"7ef301e5-7126-4564-955f-4b03fa5264a8","resolution":{"observed_at":"2026-08-11T17:24:27.567831Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T17:24:27.543969Z","title":"Robust federated learning with realistic corruption","venue":null,"work_id":"18e1c6e6-8cad-48da-be22-d37e37611c60","year":2024},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:25.952487Z"},"links":{"citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:7a236a0468f871fdf9e188394b7b00cc6d9eae4e5d916e349a669ec613a15e25","observation_id":"244228f9-02ca-4983-a48b-5215bdf59db6","resolution":{"observed_at":"2026-08-11T17:24:27.550701Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2307.13352","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T17:24:26.389226Z","title":"High dimensional distributed gradient descent with arbitrary number of byzantine attackers","venue":null,"work_id":"eac3bee4-2303-495e-aecb-085e50403350","year":2023},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:25.957547Z"},"links":{"citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:d135e66707f7ea4cfc9f9c5a7f25bdb17f412abd5f01b9f751ff5847ac97d4a2","observation_id":"3a1aaf55-3f09-427a-81f5-01b1cf835c20","resolution":{"observed_at":"2026-08-11T17:24:26.403824Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T17:24:27.525237Z","title":"Protocols for secure computations","venue":null,"work_id":"75b4a2cd-5a66-4af9-a25b-cd52c0465fb5","year":1982},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:25.963791Z"},"links":{"citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:0156fb670f5b546934949f6f17bbffd9606db8cf9e39ca201582d580f7dd7b01","observation_id":"6c648534-42a6-4730-88bd-27fdc1d9a277","resolution":{"observed_at":"2026-08-11T17:24:27.531182Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T17:24:27.507164Z","title":"Privacy preserving generative adversarial networks to model electronic health records","venue":null,"work_id":"fcbc8ae1-415d-4214-ba29-a4b62795c040","year":2022},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:25.969991Z"},"links":{"citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:e5f696b249555684357978a6123df78eb24ce611d7b9523894de13a30c60e37f","observation_id":"a12a609e-b84a-4c1d-8c79-7ea52a6333fe","resolution":{"observed_at":"2026-08-11T17:24:27.512705Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T17:24:27.479606Z","title":"Neural cleanse: Identifying and mitigating backdoor attacks in neural networks","venue":null,"work_id":"b09cc768-28a3-4639-a6c1-741b06f1fbee","year":2019},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:25.974592Z"},"links":{"citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:f4491ec78da3ab71022d0acbc62ce1a61db19f1213c62b5639738b97133a02c4","observation_id":"3d83fb98-44e3-43e4-97fb-009775feac93","resolution":{"observed_at":"2026-08-11T17:24:27.485819Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T17:24:25.979887Z","title":"A survey on contrastive self-supervised learning","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:25.979887Z"},"links":{"citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:9c9a00e89e8a3753a79227da77387232e0cebe8c3ae1f9886d428d350688aca3","observation_id":"9bcbfb0f-d7ee-4128-abf9-7b03d8e81820","resolution":{"observed_at":"2026-08-11T17:24:25.979887Z","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":"2026-08-11T17:24:27.446683Z","title":"Unsupervised visual representation learning by context prediction","venue":null,"work_id":"e529fe3e-eabc-4770-8190-3a5ad919535f","year":2015},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:25.984968Z"},"links":{"citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:56e67f5cccee2b7a69b92b656fa6372ee1913a1c9de17c0954c90a6ccdc0ab8d","observation_id":"d57a120e-95f7-4cbc-a744-c282942175cb","resolution":{"observed_at":"2026-08-11T17:24:27.452417Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1503.02531","last_updated":"2015-03-09T15:44:49Z","snapshot_observed_at":"2026-07-06T04:11:24.157003Z","submitted_at":"2015-03-09T15:44:49Z","title":"Distilling the Knowledge in a Neural Network","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1503.02531","snapshot_observed_at":"2026-08-11T17:24:25.990309Z","title":"Distilling the knowledge in a neural network","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:25.990309Z"},"links":{"cited_paper":"/paper/1503.02531","citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:68d6400e15024b721ffcbcb5a2b580f912227ef32699f3b0ea88d774d1488d93","observation_id":"80110ee1-a6fd-46d0-9334-c6d553e7843d","resolution":{"observed_at":"2026-08-11T17:24:25.990309Z","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":"2026-08-11T17:24:27.426414Z","title":"Adversarial attack on graph structured data","venue":null,"work_id":"2444d90e-37e4-4d17-8f06-516d50a2f209","year":2018},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:25.996391Z"},"links":{"citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:bf13614f6a6633554cfa78376f4b2e87332684615a931a659f32d2e22f4d4824","observation_id":"0c7dd140-dec0-479a-b1c1-0b0a6c8e37ae","resolution":{"observed_at":"2026-08-11T17:24:27.433395Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1206.6389","last_updated":"2013-03-25T10:16:36Z","snapshot_observed_at":"2026-07-06T02:50:47.096675Z","submitted_at":"2012-06-27T19:59:59Z","title":"Poisoning Attacks against Support Vector Machines","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1206.6389","snapshot_observed_at":"2026-08-11T17:24:26.002330Z","title":"Poisoning attacks against support vector ma- chines","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:26.002330Z"},"links":{"cited_paper":"/paper/1206.6389","citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:78b57b96dc3d450d94cd68598671931277448c1e1b5dbb2b51ed6404e994ad56","observation_id":"ee40af29-d022-4f59-9177-2837cb838e88","resolution":{"observed_at":"2026-08-11T17:24:26.002330Z","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":"2026-08-11T17:24:27.402910Z","title":"Protecting sensitive knowledge by data sanitization","venue":null,"work_id":"3abd1449-b37d-4c4c-a285-5ffa1833f70a","year":2003},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:26.009050Z"},"links":{"citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:4db9b4287c9a331bcb9c3b5bb087aae43e3dd6c494dd9b2d1256318b1c8ef126","observation_id":"24681ff7-bebb-46b8-8f3f-09f1589831ec","resolution":{"observed_at":"2026-08-11T17:24:27.410342Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2005.03915","last_updated":"2020-08-20T16:27:41Z","snapshot_observed_at":"2026-07-06T09:18:41.906868Z","submitted_at":"2020-05-08T09:07:38Z","title":"Defending Model Inversion and Membership Inference Attacks via Prediction Purification","version":2},"cited_work":{"arxiv_id":"2005.03915","doi":null,"metadata_source":"pith","pith_arxiv_id":"2005.03915","snapshot_observed_at":"2026-08-11T17:24:26.260581Z","title":"Defending Model Inversion and Membership Inference Attacks via Prediction Purification","venue":"cs.CR","work_id":"4c219820-af4a-4de9-a59b-4e948cc16165","year":2020},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:26.015723Z"},"links":{"cited_paper":"/paper/2005.03915","citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:b87c14304ca94d3d37b9ef4e9998c3563b0cafb96100155925d9b61bf115665d","observation_id":"d956e29d-6195-4e91-9c78-b27506d46d1f","resolution":{"observed_at":"2026-08-11T17:24:26.266624Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T17:24:27.380826Z","title":"Differential privacy: A survey of results","venue":null,"work_id":"f3656fdc-e8e2-4e53-9ce0-edcf4c006624","year":2008},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:26.023795Z"},"links":{"citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:9a25f16c1399cdd3f7f574debd3e6f09a0a82df2abd4dd62fff636e519d51076","observation_id":"b4f52ba4-f23f-4fe7-a7b0-7b820eb892be","resolution":{"observed_at":"2026-08-11T17:24:27.386931Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2202.02510","last_updated":"2022-02-08T02:06:14Z","snapshot_observed_at":"2026-08-07T09:26:00.949686Z","submitted_at":"2022-02-05T08:02:22Z","title":"A Survey on Poisoning Attacks Against Supervised Machine Learning","version":2},"cited_work":{"arxiv_id":"2202.02510","doi":null,"metadata_source":"pith","pith_arxiv_id":"2202.02510","snapshot_observed_at":"2026-08-11T17:24:26.234386Z","title":"A Survey on Poisoning Attacks Against Supervised Machine Learning","venue":"cs.CR","work_id":"0b5d041f-6e56-4d63-800c-cd369b29046d","year":2022},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:26.031800Z"},"links":{"cited_paper":"/paper/2202.02510","citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:73d06ae4cb1f271f3f97ff70577628c922acfdf2a091b6c591955684feb4db29","observation_id":"f0a72494-5677-4126-aff1-60ada85f98df","resolution":{"observed_at":"2026-08-11T17:24:26.240530Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T17:24:27.360718Z","title":"Robust loss functions under label noise for deep neural networks","venue":null,"work_id":"a4434b68-b183-452a-bab8-2cae47fcec36","year":1919},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:26.039617Z"},"links":{"citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:6df85f28dbfb1563537099241b23c2bdf7464f6f03ccfb786b69ba363ca33ac5","observation_id":"dcddf8d9-66d6-4e79-ade9-57c161e88c92","resolution":{"observed_at":"2026-08-11T17:24:27.366483Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T17:24:27.340640Z","title":"Online anomaly detection under adversarial impact","venue":null,"work_id":"9e48389f-0d6d-425f-b7e0-397b397cdd0d","year":2010},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:26.045261Z"},"links":{"citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:fb32319493cb110c445c81535bffb13a38a367406f3f962f5d20a7ce624373d7","observation_id":"34edffb4-e149-4ae1-b88b-2c451325620a","resolution":{"observed_at":"2026-08-11T17:24:27.347657Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T17:24:27.316889Z","title":"Face recognition systems: A survey","venue":null,"work_id":"b2e7b127-5fb7-4ef2-b55b-96df43bc55ba","year":2020},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:26.050659Z"},"links":{"citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:ea2d23203e4b4032f70f7b170302c5c02e1dbf2a5c92d26b3d866f43a1ed1f5c","observation_id":"1c1a70fd-37db-4f0f-ab55-3bc9dd0c6b8d","resolution":{"observed_at":"2026-08-11T17:24:27.326866Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T17:24:27.294883Z","title":"A comprehensive review on malware detection approaches","venue":null,"work_id":"0979582b-751e-4be6-9d95-0e5ac23cf426","year":2020},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:26.055809Z"},"links":{"citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:0e13568030860b57da6e86dfcfce8cd2e6d26d7398518e54fb14be61f615e199","observation_id":"120b946b-1aab-4b62-b870-cb14fbd931c2","resolution":{"observed_at":"2026-08-11T17:24:27.301620Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1507.05722","last_updated":"2015-07-27T09:54:11Z","snapshot_observed_at":"2026-08-12T00:31:49.995838Z","submitted_at":"2015-07-21T06:42:32Z","title":"A Review of Network Traffic Analysis and Prediction Techniques","version":2},"cited_work":{"arxiv_id":"1507.05722","doi":null,"metadata_source":"pith","pith_arxiv_id":"1507.05722","snapshot_observed_at":"2026-08-11T17:24:26.199814Z","title":"A Review of Network Traffic Analysis and Prediction Techniques","venue":"cs.NI","work_id":"f9a24738-916b-4007-a348-4ccf0a9eb70c","year":2015},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:26.060959Z"},"links":{"cited_paper":"/paper/1507.05722","citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:15880377da346641c12f5439cac6ced4a8115c617aaedfe617f656891f70f6c0","observation_id":"6bd75f38-be18-4321-b60f-7f694e97e63a","resolution":{"observed_at":"2026-08-11T17:24:26.209585Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.04926","last_updated":"2023-03-08T22:37:50Z","snapshot_observed_at":"2026-08-06T19:16:14.458643Z","submitted_at":"2023-03-08T22:37:50Z","title":"Automated Cyber Defence: A Review","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.04926","snapshot_observed_at":"2026-08-11T17:24:26.067370Z","title":"Automated cyber defence: A review","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:26.067370Z"},"links":{"cited_paper":"/paper/2303.04926","citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:56c241d049c77e59da5e5c9c6ada43e12346af9628250c0397b31297eac303c2","observation_id":"b16b4d08-4530-45ac-bb4d-bc48b7f687fc","resolution":{"observed_at":"2026-08-11T17:24:26.067370Z","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":"2026-08-11T17:24:27.275967Z","title":"No more chewy centers: Introducing the zero trust model of information security","venue":null,"work_id":"0e21a7e9-f02a-4625-b4fa-12f658ede46b","year":2010},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:26.073491Z"},"links":{"citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:db22e3cc910ffbfe137a76ff2404c0c70420469ebb632def7705af20dff04506","observation_id":"029b2624-a53a-4e95-b357-bd05a60586b0","resolution":{"observed_at":"2026-08-11T17:24:27.281490Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T17:24:27.255492Z","title":"Generative adversarial networks","venue":null,"work_id":"8a9f3b17-ae2b-4459-a5c1-e5032fdf98c6","year":2020},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:26.078795Z"},"links":{"citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:c5435459e2fafd700e9981f1a37835165086eef337463a74a7deaa6de1e2c560","observation_id":"40edd535-7ded-4435-92c0-c09acb80e921","resolution":{"observed_at":"2026-08-11T17:24:27.263828Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2008.12595","last_updated":"2022-07-04T16:11:08Z","snapshot_observed_at":"2026-08-11T14:30:16.364289Z","submitted_at":"2020-08-28T11:49:33Z","title":"Dynamical Variational Autoencoders: A Comprehensive Review","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2008.12595","snapshot_observed_at":"2026-08-11T17:24:26.086247Z","title":"Dynamical variational autoencoders: A comprehensive review","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:26.086247Z"},"links":{"cited_paper":"/paper/2008.12595","citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:3076f33c4a1e304d9b7f759380edfc93ca8def98fd6bb45ae296608fb184da53","observation_id":"ddc34542-0057-49a9-a69f-c74516438079","resolution":{"observed_at":"2026-08-11T17:24:26.086247Z","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":"2026-08-11T17:24:27.236053Z","title":"Secure multi-party computation: theory, practice and applications","venue":null,"work_id":"b508aea6-14d5-404c-9718-38ca8b54522c","year":2019},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:26.093121Z"},"links":{"citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:f59ef76ae6e5a83ce7a53cd5859bdab9e9b6785b3f9e9aeb7cff67cf56f937cd","observation_id":"474b858b-ed3d-46b6-9589-6da31eb329da","resolution":{"observed_at":"2026-08-11T17:24:27.242052Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T17:24:27.217946Z","title":"Homomorphic encryption","venue":null,"work_id":"e3c49941-49d7-48fa-85dc-ec03db4050e7","year":2014},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:26.101848Z"},"links":{"citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:d570d63f3452f6811680639f0d2e7b26ac3db167d544dd8196c2843cf08256df","observation_id":"69e21d91-4148-44e8-81de-5d9417a0ec29","resolution":{"observed_at":"2026-08-11T17:24:27.223530Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T17:24:27.199281Z","title":"A review of applications in federated learning","venue":null,"work_id":"59cc164b-3a6e-4911-b57e-f7704f649600","year":2020},"citing_paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses","version":2},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-11T17:24:26.108033Z"},"links":{"citing_paper":"/paper/2412.08969"},"observation_digest":"sha256:1bc242804faf1eb65358a86a8ddf8d6ff3774b56be1db11699859e676cbda17d","observation_id":"adca9c7f-9bbc-41eb-96db-cea4df5a4016","resolution":{"observed_at":"2026-08-11T17:24:27.205307Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2412.08969","last_updated":"2024-12-16T03:34:55Z","latest_version":2,"primary_category":"cs.CR","snapshot_observed_at":"2026-08-11T21:14:32.800545Z","submitted_at":"2024-12-12T06:04:20Z","title":"Deep Learning Model Security: Threats and Defenses"},"reference_resolution":{"displayed":84,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":35,"verified_exact":7,"verified_fuzzy":42},"total_outbound_references":84},"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":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"thesis":"As of 13 August 2026, this Paper Citation Record lists 84 of 84 outbound references and 2 inbound Pith citation observations for arXiv:2412.08969."}