{"as_of":"2026-08-12T08:45:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:b1bb187ea7266145eb92a3ef6295edcc7c9ed56e91d57e5a4e0962d83cb1710b","coverage":[{"denominator":69,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":69,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T20:03:56.868148Z","state":"measured"},{"denominator":69,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":69,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-12T06:34:41.77262+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2412.06149/citation-record","integrity":"/paper/2412.06149/integrity","json":"/paper/2412.06149/citation-record.json","paper":"/paper/2412.06149"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:03:57.645535Z","title":"Quantifying attention flow in transformers, 2020","venue":null,"work_id":"c59ae530-d040-44e0-956f-b16c39efb219","year":2020},"citing_paper":{"arxiv_id":"2412.06149","last_updated":"2024-12-09T02:03:27Z","snapshot_observed_at":"2026-08-12T05:27:37.102399Z","submitted_at":"2024-12-09T02:03:27Z","title":"An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-11T20:03:56.630441Z"},"links":{"citing_paper":"/paper/2412.06149"},"observation_digest":"sha256:ce0ffa32b1d2a966c107b00935fc2309d735917998db7f81d9a0fec1e400195f","observation_id":"6e886422-6a9b-42ad-92d7-55c632bc7d70","resolution":{"observed_at":"2026-08-11T20:03:57.649049Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:03:56.634865Z","title":"Backpropagation and stochastic gradient descent method","venue":null,"work_id":null,"year":1993},"citing_paper":{"arxiv_id":"2412.06149","last_updated":"2024-12-09T02:03:27Z","snapshot_observed_at":"2026-08-12T05:27:37.102399Z","submitted_at":"2024-12-09T02:03:27Z","title":"An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-11T20:03:56.634865Z"},"links":{"citing_paper":"/paper/2412.06149"},"observation_digest":"sha256:0bf7f4a30ace5e44eb68ce5541eb02342b645689cf4631b16d180a9c278d1062","observation_id":"294b1b84-298e-4af4-948b-d00cc65c65a1","resolution":{"observed_at":"2026-08-11T20:03:56.634865Z","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":"2026-08-11T20:03:57.626881Z","title":"How to backdoor federated learning","venue":null,"work_id":"ed6a53f5-7ced-4e1c-ad18-5f6c23df48f7","year":2020},"citing_paper":{"arxiv_id":"2412.06149","last_updated":"2024-12-09T02:03:27Z","snapshot_observed_at":"2026-08-12T05:27:37.102399Z","submitted_at":"2024-12-09T02:03:27Z","title":"An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-11T20:03:56.639068Z"},"links":{"citing_paper":"/paper/2412.06149"},"observation_digest":"sha256:a673b38bde997e825695712fbf00a1f2479a9fe77f746d0a16776b80f2ef9a21","observation_id":"bdecafb2-daa1-46b6-ac9d-5c4e9b80589b","resolution":{"observed_at":"2026-08-11T20:03:57.630695Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:03:57.615157Z","title":"Transformer interpretability beyond attention visualization","venue":null,"work_id":"28e69598-2be0-41c8-96aa-33b8c8c8fc5e","year":2021},"citing_paper":{"arxiv_id":"2412.06149","last_updated":"2024-12-09T02:03:27Z","snapshot_observed_at":"2026-08-12T05:27:37.102399Z","submitted_at":"2024-12-09T02:03:27Z","title":"An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-11T20:03:56.642506Z"},"links":{"citing_paper":"/paper/2412.06149"},"observation_digest":"sha256:e9649252c1b16bfe8a209b1aa8158a54fd6a0c3c0a389fe6f8af2aa97f804bfb","observation_id":"5a33122b-ca16-4628-8ea8-5b9098b9dc18","resolution":{"observed_at":"2026-08-11T20:03:57.619365Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1811.03728","last_updated":"2018-11-09T01:08:00Z","snapshot_observed_at":"2026-07-06T07:13:39.005894Z","submitted_at":"2018-11-09T01:08:00Z","title":"Detecting Backdoor Attacks on Deep Neural Networks by Activation Clustering","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1811.03728","snapshot_observed_at":"2026-08-11T20:03:56.646113Z","title":"Detecting backdoor attacks on deep neural networks by activation clustering","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.06149","last_updated":"2024-12-09T02:03:27Z","snapshot_observed_at":"2026-08-12T05:27:37.102399Z","submitted_at":"2024-12-09T02:03:27Z","title":"An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-11T20:03:56.646113Z"},"links":{"cited_paper":"/paper/1811.03728","citing_paper":"/paper/2412.06149"},"observation_digest":"sha256:fd41f416dc1482b43ca5112036d737d60c9ace0ed670c457e1072c69828f9ac3","observation_id":"55a89499-23c8-41b4-9539-b0bd679094e5","resolution":{"observed_at":"2026-08-11T20:03:56.646113Z","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":"2026-08-11T20:03:57.603017Z","title":"DeepInspect: A black-box trojan detection and mitigation frame- work for deep neural networks","venue":null,"work_id":"cdb39492-f906-4d23-bb10-4bed4edee2a2","year":2019},"citing_paper":{"arxiv_id":"2412.06149","last_updated":"2024-12-09T02:03:27Z","snapshot_observed_at":"2026-08-12T05:27:37.102399Z","submitted_at":"2024-12-09T02:03:27Z","title":"An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-11T20:03:56.650094Z"},"links":{"citing_paper":"/paper/2412.06149"},"observation_digest":"sha256:6a3de6ba2941767390179e25c8daaf49b25160f90b5aa64f62870ec83ca92bfd","observation_id":"65b8d830-ff4f-4541-9080-102de21afda1","resolution":{"observed_at":"2026-08-11T20:03:57.606719Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1712.05526","last_updated":"2017-12-15T04:26:26Z","snapshot_observed_at":"2026-07-06T06:14:30.795326Z","submitted_at":"2017-12-15T04:26:26Z","title":"Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1712.05526","snapshot_observed_at":"2026-08-11T20:03:56.653776Z","title":"Targeted backdoor attacks on deep learning systems using data poisoning","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.06149","last_updated":"2024-12-09T02:03:27Z","snapshot_observed_at":"2026-08-12T05:27:37.102399Z","submitted_at":"2024-12-09T02:03:27Z","title":"An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-11T20:03:56.653776Z"},"links":{"cited_paper":"/paper/1712.05526","citing_paper":"/paper/2412.06149"},"observation_digest":"sha256:fa54000fd8a08e516b5140dc3d421d9f105f30575ffd7d88679617a7c1616bb6","observation_id":"7ceacadd-e728-4b43-99f9-c477983260e9","resolution":{"observed_at":"2026-08-11T20:03:56.653776Z","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":"2026-08-11T20:03:57.592396Z","title":"Backdoor attacks and defenses for deep neural networks in outsourced cloud environments","venue":null,"work_id":"840b65f1-d097-40c0-8069-e745c660488f","year":2020},"citing_paper":{"arxiv_id":"2412.06149","last_updated":"2024-12-09T02:03:27Z","snapshot_observed_at":"2026-08-12T05:27:37.102399Z","submitted_at":"2024-12-09T02:03:27Z","title":"An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-11T20:03:56.657209Z"},"links":{"citing_paper":"/paper/2412.06149"},"observation_digest":"sha256:b0c1bfdb0ecd67f80335b3e56dfaf5a1708d24a0de5d8cbfec66d2e6fe74f480","observation_id":"011eb416-3c09-4da0-8231-28138e4c7cee","resolution":{"observed_at":"2026-08-11T20:03:57.595851Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:03:57.580921Z","title":"From QoS to QoE: A tutorial on video quality assessment","venue":null,"work_id":"93304209-2612-4b3e-add2-208ecafba420","year":2014},"citing_paper":{"arxiv_id":"2412.06149","last_updated":"2024-12-09T02:03:27Z","snapshot_observed_at":"2026-08-12T05:27:37.102399Z","submitted_at":"2024-12-09T02:03:27Z","title":"An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-11T20:03:56.660550Z"},"links":{"citing_paper":"/paper/2412.06149"},"observation_digest":"sha256:5e1e78f77070e683c65a621d49e71dffcadd91ccf36534f3ab492a010369b051","observation_id":"ea01ea05-c0d7-46cd-820d-8d0e311eef01","resolution":{"observed_at":"2026-08-11T20:03:57.585238Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1812.00292","last_updated":"2020-05-09T08:34:57Z","snapshot_observed_at":"2026-07-06T07:18:27.408498Z","submitted_at":"2018-12-02T00:03:07Z","title":"SentiNet: Detecting Localized Universal Attacks Against Deep Learning Systems","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1812.00292","snapshot_observed_at":"2026-08-11T20:03:56.664018Z","title":"Sentinet: Detecting physical attacks against deep learning systems","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.06149","last_updated":"2024-12-09T02:03:27Z","snapshot_observed_at":"2026-08-12T05:27:37.102399Z","submitted_at":"2024-12-09T02:03:27Z","title":"An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-11T20:03:56.664018Z"},"links":{"cited_paper":"/paper/1812.00292","citing_paper":"/paper/2412.06149"},"observation_digest":"sha256:bc80979c2c5aac1c0efc52fc18193f30967d75b801538c6b5fca6272cbb03860","observation_id":"d567b98c-f4d8-44fd-9a73-4033356d590c","resolution":{"observed_at":"2026-08-11T20:03:56.664018Z","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":"2026-08-11T20:03:57.566805Z","title":"Defending backdoor attacks on vision transformer via patch processing","venue":null,"work_id":"02db237e-7ee0-47c6-a36b-f89c7130b59a","year":2023},"citing_paper":{"arxiv_id":"2412.06149","last_updated":"2024-12-09T02:03:27Z","snapshot_observed_at":"2026-08-12T05:27:37.102399Z","submitted_at":"2024-12-09T02:03:27Z","title":"An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-11T20:03:56.668138Z"},"links":{"citing_paper":"/paper/2412.06149"},"observation_digest":"sha256:4ffbbf25a09380c3fed8e0c137939c0479cb1d432ac5127e687fe4b796955586","observation_id":"03b97f2c-6127-4c90-8780-128960a738ff","resolution":{"observed_at":"2026-08-11T20:03:57.572161Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:03:57.555731Z","title":"An image is worth 16x16 words: Transformers for image recognition at scale","venue":null,"work_id":"8f62c507-0ef9-4dfc-b135-373b56ca1137","year":2021},"citing_paper":{"arxiv_id":"2412.06149","last_updated":"2024-12-09T02:03:27Z","snapshot_observed_at":"2026-08-12T05:27:37.102399Z","submitted_at":"2024-12-09T02:03:27Z","title":"An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-11T20:03:56.671667Z"},"links":{"citing_paper":"/paper/2412.06149"},"observation_digest":"sha256:8aa6483578f6222f615bb28558afa1f910fb6ee3c04d38f4920c3951dea61fb3","observation_id":"7523a822-849a-445f-8651-0978796d408e","resolution":{"observed_at":"2026-08-11T20:03:57.559213Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:03:56.675164Z","title":"Imagenette: A smaller subset of 10 easily classified classes from imagenet","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.06149","last_updated":"2024-12-09T02:03:27Z","snapshot_observed_at":"2026-08-12T05:27:37.102399Z","submitted_at":"2024-12-09T02:03:27Z","title":"An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-11T20:03:56.675164Z"},"links":{"citing_paper":"/paper/2412.06149"},"observation_digest":"sha256:19fc3f7f8c4558bc75d99cd5ab1132f680ef787b155d6ed4956ed0445ae79e46","observation_id":"b213e805-7c08-4323-87b7-b45673f01383","resolution":{"observed_at":"2026-08-11T20:03:56.675164Z","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":"2026-08-11T20:03:57.537761Z","title":"STRIP: A defence against trojan attacks on deep neural networks","venue":null,"work_id":"4514d952-6afe-486b-8f88-f537a6467672","year":2019},"citing_paper":{"arxiv_id":"2412.06149","last_updated":"2024-12-09T02:03:27Z","snapshot_observed_at":"2026-08-12T05:27:37.102399Z","submitted_at":"2024-12-09T02:03:27Z","title":"An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-11T20:03:56.679734Z"},"links":{"citing_paper":"/paper/2412.06149"},"observation_digest":"sha256:b126f273699c0f855a9a91bf86c6ad862ba6a88b5778940f9749f02eda4714dd","observation_id":"a4b1db0a-75a1-42bf-8a26-81bee5824e26","resolution":{"observed_at":"2026-08-11T20:03:57.541398Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:03:57.526785Z","title":"Atteq-nn: Attention-based qoe-aware evasive backdoor attacks","venue":null,"work_id":"46d29d13-e27e-4717-866e-14fce0e960be","year":2022},"citing_paper":{"arxiv_id":"2412.06149","last_updated":"2024-12-09T02:03:27Z","snapshot_observed_at":"2026-08-12T05:27:37.102399Z","submitted_at":"2024-12-09T02:03:27Z","title":"An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-11T20:03:56.683222Z"},"links":{"citing_paper":"/paper/2412.06149"},"observation_digest":"sha256:7fe2380b99529c59fd0e02f9bdf3d8a50566fb0d8d9d3d8df2920a44ed604848","observation_id":"900c59e9-4ac0-4410-9f0e-fd996b4650e3","resolution":{"observed_at":"2026-08-11T20:03:57.530485Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:03:57.515798Z","title":"Coordinated backdoor attacks against federated learning with model-dependent triggers","venue":null,"work_id":"c8961bcf-1692-4dbe-9d67-10459f47bf46","year":2022},"citing_paper":{"arxiv_id":"2412.06149","last_updated":"2024-12-09T02:03:27Z","snapshot_observed_at":"2026-08-12T05:27:37.102399Z","submitted_at":"2024-12-09T02:03:27Z","title":"An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-11T20:03:56.686425Z"},"links":{"citing_paper":"/paper/2412.06149"},"observation_digest":"sha256:ec8389c8101223b23215254e11139354cdd4c40ab8e0d5823fbe062e9036e4b0","observation_id":"b2d0d31e-d61f-4616-bbf3-172d3239e4bc","resolution":{"observed_at":"2026-08-11T20:03:57.519200Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:03:57.505058Z","title":"Defense-resistant backdoor attacks against deep neural networks in outsourced cloud 15 environment","venue":null,"work_id":"bac4ab86-54da-440e-8d1a-c3b693f5ea7a","year":2021},"citing_paper":{"arxiv_id":"2412.06149","last_updated":"2024-12-09T02:03:27Z","snapshot_observed_at":"2026-08-12T05:27:37.102399Z","submitted_at":"2024-12-09T02:03:27Z","title":"An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-11T20:03:56.689855Z"},"links":{"citing_paper":"/paper/2412.06149"},"observation_digest":"sha256:ca3a774e519dc0bccba03c1ff35d81dfced0742bea75bcd946459fa872fb6929","observation_id":"f5065418-69bf-427c-acba-48a1812ec277","resolution":{"observed_at":"2026-08-11T20:03:57.508644Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:03:57.492165Z","title":"Backdoor attacks and defenses in federated learning: State-of-the- art, taxonomy, and future directions","venue":null,"work_id":"587c1def-2dd5-4165-990b-906bfc53fe91","year":2022},"citing_paper":{"arxiv_id":"2412.06149","last_updated":"2024-12-09T02:03:27Z","snapshot_observed_at":"2026-08-12T05:27:37.102399Z","submitted_at":"2024-12-09T02:03:27Z","title":"An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-11T20:03:56.693181Z"},"links":{"citing_paper":"/paper/2412.06149"},"observation_digest":"sha256:5a5b38e27c536164955f573447e72a580b9c6865bfa944a6c1c9dc2555a78993","observation_id":"76b71f23-3f7e-4138-aef4-c0c763756517","resolution":{"observed_at":"2026-08-11T20:03:57.496566Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:03:57.478033Z","title":"Redeem myself: Purifying backdoors in deep learning models using self attention distillation","venue":null,"work_id":"0c1c9c68-ef4d-4399-8522-fb2f1b6a7dff","year":2023},"citing_paper":{"arxiv_id":"2412.06149","last_updated":"2024-12-09T02:03:27Z","snapshot_observed_at":"2026-08-12T05:27:37.102399Z","submitted_at":"2024-12-09T02:03:27Z","title":"An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-11T20:03:56.697046Z"},"links":{"citing_paper":"/paper/2412.06149"},"observation_digest":"sha256:bac98049f04724adafb8f98fa988692551155cb9018c82a915d2527e67370e3c","observation_id":"373e6547-3a42-4921-b733-bdfbd952ac77","resolution":{"observed_at":"2026-08-11T20:03:57.483015Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:03:57.466072Z","title":"BadNets: Evaluating backdooring attacks on deep neural networks","venue":null,"work_id":"9b827ef8-74c5-4869-982b-f0a163e9ce81","year":2019},"citing_paper":{"arxiv_id":"2412.06149","last_updated":"2024-12-09T02:03:27Z","snapshot_observed_at":"2026-08-12T05:27:37.102399Z","submitted_at":"2024-12-09T02:03:27Z","title":"An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-11T20:03:56.700434Z"},"links":{"citing_paper":"/paper/2412.06149"},"observation_digest":"sha256:ae4b10b7e67e2c09f29385357b436222ef00dccb3eb0e11e3f51bab9432217da","observation_id":"d8c1c9e2-6caa-49f3-b471-2b5ded244958","resolution":{"observed_at":"2026-08-11T20:03:57.470366Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:03:57.455336Z","title":"Attributes-guided and pure-visual attention alignment for few- shot recognition","venue":null,"work_id":"b8438b1e-07f5-4930-a45b-577ff5236fa1","year":2021},"citing_paper":{"arxiv_id":"2412.06149","last_updated":"2024-12-09T02:03:27Z","snapshot_observed_at":"2026-08-12T05:27:37.102399Z","submitted_at":"2024-12-09T02:03:27Z","title":"An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-11T20:03:56.703265Z"},"links":{"citing_paper":"/paper/2412.06149"},"observation_digest":"sha256:3ab8ae76458d34bd5b641e4753e0122a5f7f51280f6bac43dbe11820c30391b1","observation_id":"3dac3433-1ae8-4c50-ac04-9c88ddc9f802","resolution":{"observed_at":"2026-08-11T20:03:57.459046Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1911.07399","last_updated":"2019-11-18T02:27:10Z","snapshot_observed_at":"2026-08-07T22:48:25.544977Z","submitted_at":"2019-11-18T02:27:10Z","title":"NeuronInspect: Detecting Backdoors in Neural Networks via Output Explanations","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1911.07399","snapshot_observed_at":"2026-08-11T20:03:56.706179Z","title":"Neu- ronInspect: Detecting backdoors in neural networks via output explanations","venue":null,"work_id":null,"year":1911},"citing_paper":{"arxiv_id":"2412.06149","last_updated":"2024-12-09T02:03:27Z","snapshot_observed_at":"2026-08-12T05:27:37.102399Z","submitted_at":"2024-12-09T02:03:27Z","title":"An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-11T20:03:56.706179Z"},"links":{"cited_paper":"/paper/1911.07399","citing_paper":"/paper/2412.06149"},"observation_digest":"sha256:2548b13613963ff30b259105f5274a666fb7d5332a97fa1c50c84e97cf6630fb","observation_id":"2bf65177-afef-4142-8322-bb743035f18c","resolution":{"observed_at":"2026-08-11T20:03:56.706179Z","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":"2026-08-11T20:03:57.443457Z","title":"Model-reuse attacks on deep learning systems","venue":null,"work_id":"9222725d-fc65-46f3-b2ef-d8a7093cd80e","year":2018},"citing_paper":{"arxiv_id":"2412.06149","last_updated":"2024-12-09T02:03:27Z","snapshot_observed_at":"2026-08-12T05:27:37.102399Z","submitted_at":"2024-12-09T02:03:27Z","title":"An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-11T20:03:56.709898Z"},"links":{"citing_paper":"/paper/2412.06149"},"observation_digest":"sha256:3aed9f9050b16c8c77c23a0c12075e4d9fb13588eb3fbc8e39ef77b41569929d","observation_id":"49e0351e-5dba-46cf-9b57-6fd32dc7a02b","resolution":{"observed_at":"2026-08-11T20:03:57.447495Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:03:57.431354Z","title":"Backdoor attacks against learning systems","venue":null,"work_id":"9851b932-c94d-4895-bade-d8a76754f153","year":2017},"citing_paper":{"arxiv_id":"2412.06149","last_updated":"2024-12-09T02:03:27Z","snapshot_observed_at":"2026-08-12T05:27:37.102399Z","submitted_at":"2024-12-09T02:03:27Z","title":"An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-11T20:03:56.712911Z"},"links":{"citing_paper":"/paper/2412.06149"},"observation_digest":"sha256:0f552f3f7cedbaed4c1ce80d977bb144de2b1db17eba6707dc1ce0b6bdea1af2","observation_id":"9bcc440b-ab7d-40be-a69f-32c31e046a22","resolution":{"observed_at":"2026-08-11T20:03:57.435790Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:03:56.715785Z","title":"Adam: A method for stochastic optimization","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2412.06149","last_updated":"2024-12-09T02:03:27Z","snapshot_observed_at":"2026-08-12T05:27:37.102399Z","submitted_at":"2024-12-09T02:03:27Z","title":"An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-11T20:03:56.715785Z"},"links":{"citing_paper":"/paper/2412.06149"},"observation_digest":"sha256:549f92d3399b2f374258358cddea680be5841639d64647b90d24c747986308db","observation_id":"c3d0ed00-40ab-4adc-86e0-b70386d3991e","resolution":{"observed_at":"2026-08-11T20:03:56.715785Z","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":"2026-08-11T20:03:57.413282Z","title":"Bilinear interpolation","venue":null,"work_id":"e8bec8e6-558f-4d7c-b219-c8d0e33c170a","year":2010},"citing_paper":{"arxiv_id":"2412.06149","last_updated":"2024-12-09T02:03:27Z","snapshot_observed_at":"2026-08-12T05:27:37.102399Z","submitted_at":"2024-12-09T02:03:27Z","title":"An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-11T20:03:56.718805Z"},"links":{"citing_paper":"/paper/2412.06149"},"observation_digest":"sha256:7a6587cf449b8055feaa0e3fe867570fec42dd0480831df844272c4539b5f1bf","observation_id":"9dcda7e9-5f32-49f8-afb5-2ffd0b9da191","resolution":{"observed_at":"2026-08-11T20:03:57.416530Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:03:56.721841Z","title":"Learning multiple layers of features from tiny images","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2412.06149","last_updated":"2024-12-09T02:03:27Z","snapshot_observed_at":"2026-08-12T05:27:37.102399Z","submitted_at":"2024-12-09T02:03:27Z","title":"An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-11T20:03:56.721841Z"},"links":{"citing_paper":"/paper/2412.06149"},"observation_digest":"sha256:6a4349664323f83bd8a5fa0918c767216cff5f19b252a57b8435978cab572e83","observation_id":"cea22268-dfde-49a8-8f2b-a23fa3a48b7b","resolution":{"observed_at":"2026-08-11T20:03:56.721841Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1909.02742","last_updated":"2020-08-31T04:14:46Z","snapshot_observed_at":"2026-08-10T13:53:12.701532Z","submitted_at":"2019-09-06T07:11:26Z","title":"Invisible Backdoor Attacks on Deep Neural Networks via Steganography and Regularization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1909.02742","snapshot_observed_at":"2026-08-11T20:03:56.724940Z","title":"Invisible backdoor attacks on deep neural networks via steganography and regularization","venue":null,"work_id":null,"year":1909},"citing_paper":{"arxiv_id":"2412.06149","last_updated":"2024-12-09T02:03:27Z","snapshot_observed_at":"2026-08-12T05:27:37.102399Z","submitted_at":"2024-12-09T02:03:27Z","title":"An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-11T20:03:56.724940Z"},"links":{"cited_paper":"/paper/1909.02742","citing_paper":"/paper/2412.06149"},"observation_digest":"sha256:f113fa2d757ffc55979c5e5d576de328c13e7faa6ad9f0c3e5ed9c6c430c62a9","observation_id":"a3c963e7-b54b-4abd-9203-fdfa790b5f4e","resolution":{"observed_at":"2026-08-11T20:03:56.724940Z","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":"2026-08-11T20:03:56.728911Z","title":"Neural attention distillation: Erasing backdoor triggers from deep neural networks","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.06149","last_updated":"2024-12-09T02:03:27Z","snapshot_observed_at":"2026-08-12T05:27:37.102399Z","submitted_at":"2024-12-09T02:03:27Z","title":"An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-11T20:03:56.728911Z"},"links":{"citing_paper":"/paper/2412.06149"},"observation_digest":"sha256:a7ebca580bfd763f50dc16e32575adcabd5070748f2e4605bd19eb7dec32075b","observation_id":"61572129-3321-4611-8f34-43d4996202d2","resolution":{"observed_at":"2026-08-11T20:03:56.728911Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2101.05930","last_updated":"2021-01-27T06:23:25Z","snapshot_observed_at":"2026-08-09T17:23:56.910001Z","submitted_at":"2021-01-15T01:35:22Z","title":"Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2101.05930","snapshot_observed_at":"2026-08-11T20:03:56.732625Z","title":"Neural attention distillation: Erasing backdoor triggers from deep neural networks","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.06149","last_updated":"2024-12-09T02:03:27Z","snapshot_observed_at":"2026-08-12T05:27:37.102399Z","submitted_at":"2024-12-09T02:03:27Z","title":"An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-11T20:03:56.732625Z"},"links":{"cited_paper":"/paper/2101.05930","citing_paper":"/paper/2412.06149"},"observation_digest":"sha256:79dbc1aed80369cf91ebeaeed6c6dcd5b8492fbd9db0064632a3e607c637fa41","observation_id":"ba34ffd9-5651-4bd1-ac03-32f3b0c84602","resolution":{"observed_at":"2026-08-11T20:03:56.732625Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2004.04692","last_updated":"2021-01-31T17:25:49Z","snapshot_observed_at":"2026-08-09T00:58:38.537061Z","submitted_at":"2020-04-09T17:19:37Z","title":"Rethinking the Trigger of Backdoor Attack","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2004.04692","snapshot_observed_at":"2026-08-11T20:03:56.736750Z","title":"Rethinking the trigger of backdoor attack","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2412.06149","last_updated":"2024-12-09T02:03:27Z","snapshot_observed_at":"2026-08-12T05:27:37.102399Z","submitted_at":"2024-12-09T02:03:27Z","title":"An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-11T20:03:56.736750Z"},"links":{"cited_paper":"/paper/2004.04692","citing_paper":"/paper/2412.06149"},"observation_digest":"sha256:c05bd68c6c93dd1ea26b691f336fc9bc148dc1b96f9dcaa3c445405e75762531","observation_id":"f453c190-b306-49ff-82bf-1e16f15b89e4","resolution":{"observed_at":"2026-08-11T20:03:56.736750Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1808.10307","last_updated":"2018-08-30T14:13:39Z","snapshot_observed_at":"2026-07-06T06:58:19.889839Z","submitted_at":"2018-08-30T14:13:39Z","title":"Backdoor Embedding in Convolutional Neural Network Models via Invisible Perturbation","version":1},"cited_work":{"arxiv_id":"1808.10307","doi":null,"metadata_source":"pith","pith_arxiv_id":"1808.10307","snapshot_observed_at":"2026-08-11T20:03:56.976571Z","title":"Backdoor Embedding in Convolutional Neural Network Models via Invisible Perturbation","venue":"cs.CR","work_id":"bbdfa8bf-8bf5-41f3-a5bd-687995b66570","year":2018},"citing_paper":{"arxiv_id":"2412.06149","last_updated":"2024-12-09T02:03:27Z","snapshot_observed_at":"2026-08-12T05:27:37.102399Z","submitted_at":"2024-12-09T02:03:27Z","title":"An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-11T20:03:56.740737Z"},"links":{"cited_paper":"/paper/1808.10307","citing_paper":"/paper/2412.06149"},"observation_digest":"sha256:ec139cbe2fd81a952887fc68832f75cedfa71c5ba72ecd95d13fd4044b06b877","observation_id":"1f3832b6-7834-4c76-b478-1e4d1bee76c7","resolution":{"observed_at":"2026-08-11T20:03:56.980363Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:03:57.389522Z","title":"Composite backdoor attack for deep neural network by mixing existing benign features","venue":null,"work_id":"7e5cfa3f-e603-4ee5-9f8b-619cab7a1b29","year":2020},"citing_paper":{"arxiv_id":"2412.06149","last_updated":"2024-12-09T02:03:27Z","snapshot_observed_at":"2026-08-12T05:27:37.102399Z","submitted_at":"2024-12-09T02:03:27Z","title":"An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-11T20:03:56.744521Z"},"links":{"citing_paper":"/paper/2412.06149"},"observation_digest":"sha256:87645cc688f330364f90fd4a11882b1ec29df419cf79581273ab83ee21c6180f","observation_id":"b03becf0-ae20-41cd-9039-ea5d72a8b77f","resolution":{"observed_at":"2026-08-11T20:03:57.393631Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2007.03608","last_updated":"2020-07-07T16:45:20Z","snapshot_observed_at":"2026-08-08T04:45:19.013532Z","submitted_at":"2020-07-07T16:45:20Z","title":"Backdoor attacks and defenses in feature-partitioned collaborative learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2007.03608","snapshot_observed_at":"2026-08-11T20:03:56.748111Z","title":"Backdoor attacks and defenses in feature-partitioned collaborative learning","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2412.06149","last_updated":"2024-12-09T02:03:27Z","snapshot_observed_at":"2026-08-12T05:27:37.102399Z","submitted_at":"2024-12-09T02:03:27Z","title":"An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-11T20:03:56.748111Z"},"links":{"cited_paper":"/paper/2007.03608","citing_paper":"/paper/2412.06149"},"observation_digest":"sha256:8e98c0cb8a8761a53522397d4b1735c2494d2ce022906f13219f5f1a7bbcdab3","observation_id":"74358214-83ff-49d0-b97d-051b2c76b6e0","resolution":{"observed_at":"2026-08-11T20:03:56.748111Z","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":"2026-08-11T20:03:57.378644Z","title":"ABS: Scanning neural networks for backdoors by artificial brain stimulation","venue":null,"work_id":"cdaab5a7-b5fe-4706-bea1-1160c199d9de","year":2019},"citing_paper":{"arxiv_id":"2412.06149","last_updated":"2024-12-09T02:03:27Z","snapshot_observed_at":"2026-08-12T05:27:37.102399Z","submitted_at":"2024-12-09T02:03:27Z","title":"An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-11T20:03:56.751745Z"},"links":{"citing_paper":"/paper/2412.06149"},"observation_digest":"sha256:1ec5ee36f38faeb49ef27631d9d2ea5027ef81b109609a1b9e5f1fad439f4a74","observation_id":"6d48af17-8686-4bdf-8242-c5af1465ef25","resolution":{"observed_at":"2026-08-11T20:03:57.382552Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:03:57.367965Z","title":"Trojaning attack on neural networks","venue":null,"work_id":"aeb92a6c-735f-471c-979b-abcd31f73c82","year":2018},"citing_paper":{"arxiv_id":"2412.06149","last_updated":"2024-12-09T02:03:27Z","snapshot_observed_at":"2026-08-12T05:27:37.102399Z","submitted_at":"2024-12-09T02:03:27Z","title":"An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-11T20:03:56.754946Z"},"links":{"citing_paper":"/paper/2412.06149"},"observation_digest":"sha256:c41a2d35b604e902257ef9b07e3c8108c24a780e8c60ddd408d9164a4c2562fb","observation_id":"ecfe0e5f-4f94-4383-8810-75bc1c60c8b8","resolution":{"observed_at":"2026-08-11T20:03:57.371847Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2111.11870","last_updated":"2021-11-22T08:13:51Z","snapshot_observed_at":"2026-07-06T12:11:24.221800Z","submitted_at":"2021-11-22T08:13:51Z","title":"DBIA: Data-free Backdoor Injection Attack against Transformer Networks","version":1},"cited_work":{"arxiv_id":"2111.11870","doi":null,"metadata_source":"pith","pith_arxiv_id":"2111.11870","snapshot_observed_at":"2026-08-11T20:03:56.950200Z","title":"DBIA: Data-free Backdoor Injection Attack against Transformer Networks","venue":"cs.CV","work_id":"ab920c01-230b-4b85-aeb7-944836853314","year":2021},"citing_paper":{"arxiv_id":"2412.06149","last_updated":"2024-12-09T02:03:27Z","snapshot_observed_at":"2026-08-12T05:27:37.102399Z","submitted_at":"2024-12-09T02:03:27Z","title":"An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-11T20:03:56.758204Z"},"links":{"cited_paper":"/paper/2111.11870","citing_paper":"/paper/2412.06149"},"observation_digest":"sha256:e880241cd4bc272cad624eb12ec75f7d59341867295b61c64a17fd1e4c12c840","observation_id":"0b051119-5f2c-4e15-9268-ccb8616bc898","resolution":{"observed_at":"2026-08-11T20:03:56.954507Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:03:57.357970Z","title":"NIC: Detecting adversarial samples with neural network invariant checking","venue":null,"work_id":"73d04e88-1104-4de8-a460-13140fcdfdf1","year":2019},"citing_paper":{"arxiv_id":"2412.06149","last_updated":"2024-12-09T02:03:27Z","snapshot_observed_at":"2026-08-12T05:27:37.102399Z","submitted_at":"2024-12-09T02:03:27Z","title":"An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-11T20:03:56.761450Z"},"links":{"citing_paper":"/paper/2412.06149"},"observation_digest":"sha256:839c2c01c497c7f5bbeb5063f9340791aec14b5fb08712febba0d64cfee28b75","observation_id":"5be2094e-3c22-4117-b66d-558b085a0755","resolution":{"observed_at":"2026-08-11T20:03:57.361199Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:03:57.346654Z","title":"Distributed representations of words and phrases and their compositionality","venue":null,"work_id":"a51ef690-74a2-4848-9b1a-8d79425a04ad","year":2013},"citing_paper":{"arxiv_id":"2412.06149","last_updated":"2024-12-09T02:03:27Z","snapshot_observed_at":"2026-08-12T05:27:37.102399Z","submitted_at":"2024-12-09T02:03:27Z","title":"An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-11T20:03:56.764532Z"},"links":{"citing_paper":"/paper/2412.06149"},"observation_digest":"sha256:1734f31f1a3a27a13693996cb928e0581268c914b3f937779e2e9e3c6d65eb18","observation_id":"9e0e9290-07e9-4804-a7b2-215c561fd7d0","resolution":{"observed_at":"2026-08-11T20:03:57.350855Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:03:57.334878Z","title":"Visual slam for automated driving: Exploring the applications of deep learning","venue":null,"work_id":"95cf84ab-832a-415e-ae3d-3455ab3fdf19","year":2018},"citing_paper":{"arxiv_id":"2412.06149","last_updated":"2024-12-09T02:03:27Z","snapshot_observed_at":"2026-08-12T05:27:37.102399Z","submitted_at":"2024-12-09T02:03:27Z","title":"An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-11T20:03:56.767868Z"},"links":{"citing_paper":"/paper/2412.06149"},"observation_digest":"sha256:aed0a3e6d6a07ea53a1b16330190a66665c39e2b26bda1931fe9fe68092db18e","observation_id":"871d685d-7558-4349-bc53-0fc04196971b","resolution":{"observed_at":"2026-08-11T20:03:57.338901Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1406.6247","last_updated":"2014-06-24T14:16:56Z","snapshot_observed_at":"2026-08-04T03:49:45.521904Z","submitted_at":"2014-06-24T14:16:56Z","title":"Recurrent Models of Visual Attention","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1406.6247","snapshot_observed_at":"2026-08-11T20:03:56.771267Z","title":"Recurrent models of visual attention","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2412.06149","last_updated":"2024-12-09T02:03:27Z","snapshot_observed_at":"2026-08-12T05:27:37.102399Z","submitted_at":"2024-12-09T02:03:27Z","title":"An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-11T20:03:56.771267Z"},"links":{"cited_paper":"/paper/1406.6247","citing_paper":"/paper/2412.06149"},"observation_digest":"sha256:a333424b3530f3e765efabef3d162d209f7acabfa5e96893fa27493792b3310b","observation_id":"377b3921-933a-49ce-9102-a4d3d2993734","resolution":{"observed_at":"2026-08-11T20:03:56.771267Z","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":"2026-08-11T20:03:57.324335Z","title":"Machine learning with membership privacy using adversarial regularization","venue":null,"work_id":"6def52f5-a09d-4e2f-a46c-428f2f11e0eb","year":2018},"citing_paper":{"arxiv_id":"2412.06149","last_updated":"2024-12-09T02:03:27Z","snapshot_observed_at":"2026-08-12T05:27:37.102399Z","submitted_at":"2024-12-09T02:03:27Z","title":"An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-11T20:03:56.775191Z"},"links":{"citing_paper":"/paper/2412.06149"},"observation_digest":"sha256:a8b7245fd1ef2d0fb5fad15b0aad2d7ccafd1c4a1ce3bb12582707a265615b37","observation_id":"59be5193-939a-4a6c-a335-b0d9ed1efa79","resolution":{"observed_at":"2026-08-11T20:03:57.327827Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:03:57.313901Z","title":"Input-aware dynamic backdoor attack","venue":null,"work_id":"67ff6c1d-ca6f-494f-8aca-c97f78f05c80","year":2020},"citing_paper":{"arxiv_id":"2412.06149","last_updated":"2024-12-09T02:03:27Z","snapshot_observed_at":"2026-08-12T05:27:37.102399Z","submitted_at":"2024-12-09T02:03:27Z","title":"An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-11T20:03:56.779022Z"},"links":{"citing_paper":"/paper/2412.06149"},"observation_digest":"sha256:a577f0ecf0925213366356e3728fc33a8c4822b46040976fcb8906360a269a2f","observation_id":"4deeec66-c4e4-4ee6-bdbf-3aece55f467b","resolution":{"observed_at":"2026-08-11T20:03:57.317423Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2102.10369","last_updated":"2021-03-04T04:09:38Z","snapshot_observed_at":"2026-08-02T13:52:44.392403Z","submitted_at":"2021-02-20T15:25:36Z","title":"WaNet -- Imperceptible Warping-based Backdoor Attack","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2102.10369","snapshot_observed_at":"2026-08-11T20:03:56.782562Z","title":"Wanet–imperceptible warping-based backdoor attack","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.06149","last_updated":"2024-12-09T02:03:27Z","snapshot_observed_at":"2026-08-12T05:27:37.102399Z","submitted_at":"2024-12-09T02:03:27Z","title":"An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-11T20:03:56.782562Z"},"links":{"cited_paper":"/paper/2102.10369","citing_paper":"/paper/2412.06149"},"observation_digest":"sha256:1731d7b751b78fe685b4b22212af8573e50144ba7a0c3f3d93b0d81f74eb2da4","observation_id":"3ec75a3b-7a50-4daf-b783-02fd98752e2d","resolution":{"observed_at":"2026-08-11T20:03:56.782562Z","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":"2026-08-11T20:03:57.303165Z","title":"A tale of evil twins: Adversarial inputs versus poisoned models","venue":null,"work_id":"23a00235-7b91-4210-848a-179b5d966b3a","year":2020},"citing_paper":{"arxiv_id":"2412.06149","last_updated":"2024-12-09T02:03:27Z","snapshot_observed_at":"2026-08-12T05:27:37.102399Z","submitted_at":"2024-12-09T02:03:27Z","title":"An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-11T20:03:56.786406Z"},"links":{"citing_paper":"/paper/2412.06149"},"observation_digest":"sha256:c05701c7284c358ea4a16ac2cfb2a76d6a74d46f8ade9e7d6477306077ec38db","observation_id":"3a255342-8766-4039-8d6d-b5c28c0a43ec","resolution":{"observed_at":"2026-08-11T20:03:57.306782Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:03:57.290439Z","title":"You only look once: Unified, real-time object detection","venue":null,"work_id":"bfc3b8b2-ae25-4714-9e12-d8345afdda9a","year":2016},"citing_paper":{"arxiv_id":"2412.06149","last_updated":"2024-12-09T02:03:27Z","snapshot_observed_at":"2026-08-12T05:27:37.102399Z","submitted_at":"2024-12-09T02:03:27Z","title":"An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-11T20:03:56.790003Z"},"links":{"citing_paper":"/paper/2412.06149"},"observation_digest":"sha256:2d47917a4109e786725e8550aca1cbbfd5b8691fc9aa0efa062590dc7f9bb869","observation_id":"f1b95dd2-fb6e-430a-ab34-405e5f174845","resolution":{"observed_at":"2026-08-11T20:03:57.294854Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:03:57.278211Z","title":"Hidden trigger backdoor attacks","venue":null,"work_id":"0597b50a-9240-4e83-b233-ddfc726d3bf5","year":2020},"citing_paper":{"arxiv_id":"2412.06149","last_updated":"2024-12-09T02:03:27Z","snapshot_observed_at":"2026-08-12T05:27:37.102399Z","submitted_at":"2024-12-09T02:03:27Z","title":"An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-11T20:03:56.793523Z"},"links":{"citing_paper":"/paper/2412.06149"},"observation_digest":"sha256:85b87616bbb9e226e33527725532d58679a5198fb8e041f2fb0b335993969cb8","observation_id":"17434b77-6e25-402e-8d84-1c75fd271934","resolution":{"observed_at":"2026-08-11T20:03:57.282228Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:03:57.267297Z","title":"Dynamic backdoor attacks against machine learning models","venue":null,"work_id":"42c1e92a-1973-4850-a743-c020318852bd","year":2022},"citing_paper":{"arxiv_id":"2412.06149","last_updated":"2024-12-09T02:03:27Z","snapshot_observed_at":"2026-08-12T05:27:37.102399Z","submitted_at":"2024-12-09T02:03:27Z","title":"An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-11T20:03:56.796888Z"},"links":{"citing_paper":"/paper/2412.06149"},"observation_digest":"sha256:966ecd7129c6b317b138cb675eebdc5a0bcf74b468335bcc9471dc24595cdd7d","observation_id":"c7e3e51f-370a-4fd5-ac79-a16f83695f8d","resolution":{"observed_at":"2026-08-11T20:03:57.270869Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:03:57.256804Z","title":"Facenet: A unified embedding for face recognition and clustering","venue":null,"work_id":"27276f91-af5c-4f2d-93bd-e487c20d87bc","year":2015},"citing_paper":{"arxiv_id":"2412.06149","last_updated":"2024-12-09T02:03:27Z","snapshot_observed_at":"2026-08-12T05:27:37.102399Z","submitted_at":"2024-12-09T02:03:27Z","title":"An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-11T20:03:56.800322Z"},"links":{"citing_paper":"/paper/2412.06149"},"observation_digest":"sha256:080309b544b438e6c7fd7f7ddc7ef485004b1be99b93e8fb748d4cad7f799d28","observation_id":"cb5a2f7a-9bfb-4f15-88dd-46a7d8782d97","resolution":{"observed_at":"2026-08-11T20:03:57.260098Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:03:57.245124Z","title":null,"venue":null,"work_id":"5a5f5a19-ba00-4643-8b60-fc506dd750fe","year":2012},"citing_paper":{"arxiv_id":"2412.06149","last_updated":"2024-12-09T02:03:27Z","snapshot_observed_at":"2026-08-12T05:27:37.102399Z","submitted_at":"2024-12-09T02:03:27Z","title":"An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-11T20:03:56.803165Z"},"links":{"citing_paper":"/paper/2412.06149"},"observation_digest":"sha256:14a82232a4a153559617e9241ad1800c9e95f4aa768230092f1bd708087e87c1","observation_id":"3a6235cb-f719-4286-a303-1f4c4b408e9a","resolution":{"observed_at":"2026-08-11T20:03:57.248914Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.08477","last_updated":"2022-06-16T22:55:32Z","snapshot_observed_at":"2026-08-06T14:23:54.932442Z","submitted_at":"2022-06-16T22:55:32Z","title":"Backdoor Attacks on Vision Transformers","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.08477","snapshot_observed_at":"2026-08-11T20:03:56.806308Z","title":"Backdoor attacks on vision transformers","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.06149","last_updated":"2024-12-09T02:03:27Z","snapshot_observed_at":"2026-08-12T05:27:37.102399Z","submitted_at":"2024-12-09T02:03:27Z","title":"An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-11T20:03:56.806308Z"},"links":{"cited_paper":"/paper/2206.08477","citing_paper":"/paper/2412.06149"},"observation_digest":"sha256:36bc4e4199164e71ea969184cd306481f93e0912f4bce5fc1132053f99336fef","observation_id":"3cafd878-0c7a-4f7f-8f94-fb7e74acc05f","resolution":{"observed_at":"2026-08-11T20:03:56.806308Z","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":"2026-08-11T20:03:57.233575Z","title":"Spectral signatures in backdoor attacks","venue":null,"work_id":"3b827ebd-ebe2-46dc-a3ad-c5aa9f304cd3","year":2018},"citing_paper":{"arxiv_id":"2412.06149","last_updated":"2024-12-09T02:03:27Z","snapshot_observed_at":"2026-08-12T05:27:37.102399Z","submitted_at":"2024-12-09T02:03:27Z","title":"An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-11T20:03:56.809388Z"},"links":{"citing_paper":"/paper/2412.06149"},"observation_digest":"sha256:480ec168ca62740f0e4ac69e759ff73864e03dc241a1e15a1b6bff62a30fd773","observation_id":"a3f90882-f3c4-4f0f-9cfc-dec5aeb28b27","resolution":{"observed_at":"2026-08-11T20:03:57.237324Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1908.02203","last_updated":"2022-03-31T12:22:35Z","snapshot_observed_at":"2026-07-06T08:12:43.653835Z","submitted_at":"2019-08-06T15:11:37Z","title":"Model Agnostic Defence against Backdoor Attacks in Machine Learning","version":3},"cited_work":{"arxiv_id":"1908.02203","doi":null,"metadata_source":"pith","pith_arxiv_id":"1908.02203","snapshot_observed_at":"2026-08-11T20:03:56.899013Z","title":"Model Agnostic Defence against Backdoor Attacks in Machine Learning","venue":"cs.LG","work_id":"bba602c3-0fa3-4d39-a253-8fbaf5e43ea5","year":2019},"citing_paper":{"arxiv_id":"2412.06149","last_updated":"2024-12-09T02:03:27Z","snapshot_observed_at":"2026-08-12T05:27:37.102399Z","submitted_at":"2024-12-09T02:03:27Z","title":"An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-11T20:03:56.812300Z"},"links":{"cited_paper":"/paper/1908.02203","citing_paper":"/paper/2412.06149"},"observation_digest":"sha256:ad25b74969edc98eaaafd91828d5efa2ea063bbda29e64ee9c51b988add4cf03","observation_id":"cf56f384-c73a-4f62-839b-828927e4b93b","resolution":{"observed_at":"2026-08-11T20:03:56.905514Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:03:56.815636Z","title":"Attention is all you need","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.06149","last_updated":"2024-12-09T02:03:27Z","snapshot_observed_at":"2026-08-12T05:27:37.102399Z","submitted_at":"2024-12-09T02:03:27Z","title":"An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-11T20:03:56.815636Z"},"links":{"citing_paper":"/paper/2412.06149"},"observation_digest":"sha256:d30e780bc239aacb32d1e2b6e275cae1356c7c4496b14047d0a179a23ddb1a87","observation_id":"7ee0bcec-3ee7-42e6-b2a1-b87a49b5e964","resolution":{"observed_at":"2026-08-11T20:03:56.815636Z","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":"2026-08-11T20:03:57.216371Z","title":"Neural cleanse: Identifying and mitigating backdoor attacks in neural networks","venue":null,"work_id":"b58145ad-0900-4a86-8d18-126c52227108","year":2019},"citing_paper":{"arxiv_id":"2412.06149","last_updated":"2024-12-09T02:03:27Z","snapshot_observed_at":"2026-08-12T05:27:37.102399Z","submitted_at":"2024-12-09T02:03:27Z","title":"An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-11T20:03:56.818494Z"},"links":{"citing_paper":"/paper/2412.06149"},"observation_digest":"sha256:53ee59ff58fc264faaf985eea9998478e4601c85cc3d917a6934bd7f43b75f48","observation_id":"beae34bd-5abc-4b2f-9ad2-7549f2e630bb","resolution":{"observed_at":"2026-08-11T20:03:57.219851Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:03:57.206059Z","title":"Residual attention network for image classification","venue":null,"work_id":"b3491476-d69d-4652-be35-0baf4650c7a4","year":2017},"citing_paper":{"arxiv_id":"2412.06149","last_updated":"2024-12-09T02:03:27Z","snapshot_observed_at":"2026-08-12T05:27:37.102399Z","submitted_at":"2024-12-09T02:03:27Z","title":"An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-11T20:03:56.821982Z"},"links":{"citing_paper":"/paper/2412.06149"},"observation_digest":"sha256:91bbeea6460392f76eac13d04b4abfa41c3be0e33628426aed3cb8fbc4b51073","observation_id":"63cf0296-bb9a-4da4-b544-e4a005a5c56b","resolution":{"observed_at":"2026-08-11T20:03:57.209493Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:03:57.195943Z","title":"Papailiopoulos","venue":null,"work_id":"6d0605a1-46ea-4938-9e7f-01694f9b4d05","year":2020},"citing_paper":{"arxiv_id":"2412.06149","last_updated":"2024-12-09T02:03:27Z","snapshot_observed_at":"2026-08-12T05:27:37.102399Z","submitted_at":"2024-12-09T02:03:27Z","title":"An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-11T20:03:56.825616Z"},"links":{"citing_paper":"/paper/2412.06149"},"observation_digest":"sha256:acc59beb812ded7768d511819264e18c7c18fe7b1b7dbda4fd0edcde229a3550","observation_id":"38ab6e9e-4b9b-415d-b28c-cb607a704eef","resolution":{"observed_at":"2026-08-11T20:03:57.199286Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:03:57.185281Z","title":"Backdoor attacks against transfer learning with pre-trained deep learning models","venue":null,"work_id":"0425ed6e-a372-4c64-85dc-33d0914ff634","year":2020},"citing_paper":{"arxiv_id":"2412.06149","last_updated":"2024-12-09T02:03:27Z","snapshot_observed_at":"2026-08-12T05:27:37.102399Z","submitted_at":"2024-12-09T02:03:27Z","title":"An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-11T20:03:56.829135Z"},"links":{"citing_paper":"/paper/2412.06149"},"observation_digest":"sha256:0735d2b7ac20e83731a74d01453ecc6c598d6c1006cd4c89b7fe950e705b2801","observation_id":"db93f875-2504-4c88-87c6-844a754221f2","resolution":{"observed_at":"2026-08-11T20:03:57.188955Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:03:57.174075Z","title":"Image quality assessment: From error visibility to structural 16 similarity","venue":null,"work_id":"ea9cab6f-92ab-4675-ae8d-9bce689ab85b","year":2004},"citing_paper":{"arxiv_id":"2412.06149","last_updated":"2024-12-09T02:03:27Z","snapshot_observed_at":"2026-08-12T05:27:37.102399Z","submitted_at":"2024-12-09T02:03:27Z","title":"An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-11T20:03:56.832968Z"},"links":{"citing_paper":"/paper/2412.06149"},"observation_digest":"sha256:2353cdda277bd672d74fafc014c8ca5401309f591937df5bd69cd6b66db3c90e","observation_id":"77a81ecd-35c8-4c9f-a08a-93d8c2100515","resolution":{"observed_at":"2026-08-11T20:03:57.177902Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:03:57.164455Z","title":"DBA: Distributed backdoor attacks against federated learning","venue":null,"work_id":"ab1561b7-f205-4dc5-8915-01782df59449","year":2019},"citing_paper":{"arxiv_id":"2412.06149","last_updated":"2024-12-09T02:03:27Z","snapshot_observed_at":"2026-08-12T05:27:37.102399Z","submitted_at":"2024-12-09T02:03:27Z","title":"An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-11T20:03:56.836615Z"},"links":{"citing_paper":"/paper/2412.06149"},"observation_digest":"sha256:112226f8dd8f6a2b7b8806b506b5655382b40cdcaa15bfb96936f8fdc2514dc8","observation_id":"f85af807-bd8c-4d8c-b27d-b3891b253ead","resolution":{"observed_at":"2026-08-11T20:03:57.167702Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:03:57.154606Z","title":"Detecting ai trojans using meta neural analysis","venue":null,"work_id":"bc97f30d-10fd-417e-bd8b-741c5978c201","year":2021},"citing_paper":{"arxiv_id":"2412.06149","last_updated":"2024-12-09T02:03:27Z","snapshot_observed_at":"2026-08-12T05:27:37.102399Z","submitted_at":"2024-12-09T02:03:27Z","title":"An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-11T20:03:56.840539Z"},"links":{"citing_paper":"/paper/2412.06149"},"observation_digest":"sha256:4e570c0dcb9acfadf4d90dfcf9df412893471c6776b71ec29ae3282d59b01cce","observation_id":"02680687-54d8-40ef-afda-378339502df5","resolution":{"observed_at":"2026-08-11T20:03:57.157794Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:03:57.143062Z","title":"Countermeasure against backdoor attacks using epistemic classifiers","venue":null,"work_id":"00b2f98e-21ee-41f7-99d7-253f85eb43b1","year":2020},"citing_paper":{"arxiv_id":"2412.06149","last_updated":"2024-12-09T02:03:27Z","snapshot_observed_at":"2026-08-12T05:27:37.102399Z","submitted_at":"2024-12-09T02:03:27Z","title":"An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-11T20:03:56.844262Z"},"links":{"citing_paper":"/paper/2412.06149"},"observation_digest":"sha256:2e010a191aba2fd81617ef893fc1047d07b543cd1346ee6cfde11f44464e81bb","observation_id":"0166cafe-aa33-42bd-81d2-e41a7c12287b","resolution":{"observed_at":"2026-08-11T20:03:57.147111Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:03:57.132457Z","title":"Latent backdoor attacks on deep neural networks","venue":null,"work_id":"65a656c7-d9f5-4b66-b71a-84adf979f4fb","year":2019},"citing_paper":{"arxiv_id":"2412.06149","last_updated":"2024-12-09T02:03:27Z","snapshot_observed_at":"2026-08-12T05:27:37.102399Z","submitted_at":"2024-12-09T02:03:27Z","title":"An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-11T20:03:56.847833Z"},"links":{"citing_paper":"/paper/2412.06149"},"observation_digest":"sha256:cdd78f952fc86be88bb0822d4ae0f0ffb6a9157bae6c627788f33e9178f2bef7","observation_id":"d56e994c-088c-4459-a582-74eb51aa2166","resolution":{"observed_at":"2026-08-11T20:03:57.136272Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:03:57.121057Z","title":null,"venue":null,"work_id":"07ee10db-18c0-4a32-8490-ea99fb54a8ef","year":2023},"citing_paper":{"arxiv_id":"2412.06149","last_updated":"2024-12-09T02:03:27Z","snapshot_observed_at":"2026-08-12T05:27:37.102399Z","submitted_at":"2024-12-09T02:03:27Z","title":"An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-11T20:03:56.851392Z"},"links":{"citing_paper":"/paper/2412.06149"},"observation_digest":"sha256:5986118cdb52794c6cf72fdfa05be6d2d0ab1542b1f639399627c69eb0090bc8","observation_id":"9c7d9184-e502-493e-b1a2-4b3eed4e5ea1","resolution":{"observed_at":"2026-08-11T20:03:57.125210Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:03:57.110141Z","title":"The unreasonable effectiveness of deep features as a perceptual metric","venue":null,"work_id":"942d14f3-fa27-44a8-9c34-1a0cbf8d2e19","year":2018},"citing_paper":{"arxiv_id":"2412.06149","last_updated":"2024-12-09T02:03:27Z","snapshot_observed_at":"2026-08-12T05:27:37.102399Z","submitted_at":"2024-12-09T02:03:27Z","title":"An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-11T20:03:56.854886Z"},"links":{"citing_paper":"/paper/2412.06149"},"observation_digest":"sha256:57747ee4e35efe7f5752f8eef48aefe3ccbd1df3122905bd54a6e409722437ca","observation_id":"a12161e6-35e5-4be0-9c81-1acf8f744311","resolution":{"observed_at":"2026-08-11T20:03:57.113528Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:03:57.100402Z","title":"Trojvit: Trojan insertion in vision transformers","venue":null,"work_id":"9bf7a002-8f15-4abb-8905-6de045eba7ff","year":2023},"citing_paper":{"arxiv_id":"2412.06149","last_updated":"2024-12-09T02:03:27Z","snapshot_observed_at":"2026-08-12T05:27:37.102399Z","submitted_at":"2024-12-09T02:03:27Z","title":"An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-11T20:03:56.858061Z"},"links":{"citing_paper":"/paper/2412.06149"},"observation_digest":"sha256:c4a53aa803b7df8df9cdf41d2b39f7355ca65ad2cdf6873edcc24e87b58c5107","observation_id":"ff97482d-10eb-4104-bab9-b6cfb2b839cd","resolution":{"observed_at":"2026-08-11T20:03:57.103750Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:03:57.089914Z","title":"Parallelized stochastic gradient descent","venue":null,"work_id":"d7bdbb6b-3cab-4fe1-a50a-0b7664e42283","year":2010},"citing_paper":{"arxiv_id":"2412.06149","last_updated":"2024-12-09T02:03:27Z","snapshot_observed_at":"2026-08-12T05:27:37.102399Z","submitted_at":"2024-12-09T02:03:27Z","title":"An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-11T20:03:56.861491Z"},"links":{"citing_paper":"/paper/2412.06149"},"observation_digest":"sha256:29df80d575be4199dba5fea9ea0592606e4caa62630a689c0448dd9275512aad","observation_id":"13b86801-f3cb-4f82-8865-4bc943f77448","resolution":{"observed_at":"2026-08-11T20:03:57.093179Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:03:57.065398Z","title":"Top Minds","venue":null,"work_id":"7b227d83-dcea-4c78-8f84-832c3f3eb0c5","year":2018},"citing_paper":{"arxiv_id":"2412.06149","last_updated":"2024-12-09T02:03:27Z","snapshot_observed_at":"2026-08-12T05:27:37.102399Z","submitted_at":"2024-12-09T02:03:27Z","title":"An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers","version":1},"reference_index":2018,"source":"pdf_text","source_observed_at":"2026-08-11T20:03:56.868148Z"},"links":{"citing_paper":"/paper/2412.06149"},"observation_digest":"sha256:5820d01b2b659f2f2edf1e87df84f17e21655ef2d6d3e6f4f8a5622daf560eb0","observation_id":"d850e27e-3d1e-4207-8ee8-bf8670f4751b","resolution":{"observed_at":"2026-08-11T20:03:57.069965Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:03:57.078848Z","title":"His research interests include the Internet of Things, smart sensing, and AI security","venue":null,"work_id":"d09fa3d0-2078-48b2-8f9b-89fe6b4e855e","year":2010},"citing_paper":{"arxiv_id":"2412.06149","last_updated":"2024-12-09T02:03:27Z","snapshot_observed_at":"2026-08-12T05:27:37.102399Z","submitted_at":"2024-12-09T02:03:27Z","title":"An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers","version":1},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-11T20:03:56.864858Z"},"links":{"citing_paper":"/paper/2412.06149"},"observation_digest":"sha256:b883931f6507f5ce88933b9cd4188e81adcb5bba5a88a5988d093359f57b7c62","observation_id":"7a435342-2225-417e-b010-dd84db44e11b","resolution":{"observed_at":"2026-08-11T20:03:57.082823Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2412.06149","last_updated":"2024-12-09T02:03:27Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-12T05:27:37.102399Z","submitted_at":"2024-12-09T02:03:27Z","title":"An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers"},"reference_resolution":{"displayed":69,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":19,"verified_exact":3,"verified_fuzzy":47},"total_outbound_references":69},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"thesis":"As of 12 August 2026, this Paper Citation Record lists 69 of 69 outbound references and 0 inbound Pith citation observations for arXiv:2412.06149."}