{"as_of":"2026-08-15T16:10:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:93eb1af81e65ff9f3e02c70f64186460a44364602dfcbe31ded5ef7e0a554168","coverage":[{"denominator":34,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":34,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T17:33:53.329238Z","state":"measured"},{"denominator":34,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":34,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-15T06:32:42.880941+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/2507.10491/citation-record","integrity":"/paper/2507.10491/integrity","json":"/paper/2507.10491/citation-record.json","paper":"/paper/2507.10491"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:33:56.260154Z","title":"Superdeepfool: a new fast and accurate minimal adversarial attack","venue":null,"work_id":"743e9cef-627c-4879-a50c-841f21164e0b","year":2025},"citing_paper":{"arxiv_id":"2507.10491","last_updated":"2025-07-14T17:13:06Z","snapshot_observed_at":"2026-08-10T20:21:34.860714Z","submitted_at":"2025-07-14T17:13:06Z","title":"BURN: Backdoor Unlearning via Adversarial Boundary Analysis","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T17:33:48.051035Z"},"links":{"citing_paper":"/paper/2507.10491"},"observation_digest":"sha256:8e3f20b59b4ac5820ed94ecd6934f3e96f49df4d9a821d0abda4ce1dd60b1f8d","observation_id":"4bb7599a-dabe-4449-9b25-d1438c9d43f2","resolution":{"observed_at":"2026-08-06T17:33:56.330670Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T17:33:56.056060Z","title":"Blind backdoors in deep learning models","venue":null,"work_id":"14d25cb5-6ec0-42f3-8123-f0e2187fe74e","year":2021},"citing_paper":{"arxiv_id":"2507.10491","last_updated":"2025-07-14T17:13:06Z","snapshot_observed_at":"2026-08-10T20:21:34.860714Z","submitted_at":"2025-07-14T17:13:06Z","title":"BURN: Backdoor Unlearning via Adversarial Boundary Analysis","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T17:33:48.154208Z"},"links":{"citing_paper":"/paper/2507.10491"},"observation_digest":"sha256:2af7b8dca6d7bf1f1ed7809505b1a8fb302adee1219d14821f3de4c1a7cb90b2","observation_id":"8f50b441-a439-42ed-9d86-b6ca9b07a274","resolution":{"observed_at":"2026-08-06T17:33:56.155947Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T17:33:48.320522Z","title":"Targeted backdoor attacks on deep learning systems using data poisoning","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.10491","last_updated":"2025-07-14T17:13:06Z","snapshot_observed_at":"2026-08-10T20:21:34.860714Z","submitted_at":"2025-07-14T17:13:06Z","title":"BURN: Backdoor Unlearning via Adversarial Boundary Analysis","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T17:33:48.320522Z"},"links":{"cited_paper":"/paper/1712.05526","citing_paper":"/paper/2507.10491"},"observation_digest":"sha256:7b5ea0c56256522321d07624a5515dd7e6106b3dd1d85be097f1d95cc175f248","observation_id":"3232fc75-3be1-45da-a6f2-25c8e35b8e3b","resolution":{"observed_at":"2026-08-06T17:33:48.320522Z","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":"2026-08-06T17:33:48.491804Z","title":"Imagenet: A large-scale hierarchical image database","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2507.10491","last_updated":"2025-07-14T17:13:06Z","snapshot_observed_at":"2026-08-10T20:21:34.860714Z","submitted_at":"2025-07-14T17:13:06Z","title":"BURN: Backdoor Unlearning via Adversarial Boundary Analysis","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T17:33:48.491804Z"},"links":{"citing_paper":"/paper/2507.10491"},"observation_digest":"sha256:5df32489ca233f6a4198bf63da61d0c9214a37c2dbe5afc4a30ef77cead564b6","observation_id":"f54b9ff4-5d9f-40aa-926a-c9a3502eab09","resolution":{"observed_at":"2026-08-06T17:33:48.491804Z","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":"2026-08-06T17:33:55.841079Z","title":"Lira: Learnable, imperceptible and robust backdoor attacks","venue":null,"work_id":"2288bdfc-0dc2-4df8-9098-458050e8be68","year":2021},"citing_paper":{"arxiv_id":"2507.10491","last_updated":"2025-07-14T17:13:06Z","snapshot_observed_at":"2026-08-10T20:21:34.860714Z","submitted_at":"2025-07-14T17:13:06Z","title":"BURN: Backdoor Unlearning via Adversarial Boundary Analysis","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T17:33:48.645320Z"},"links":{"citing_paper":"/paper/2507.10491"},"observation_digest":"sha256:24d6df3e65c9b6476ecb4fdba0f0bbdbee10469983b1687f419c0273d6b8d734","observation_id":"32f8017d-009c-4fd8-9f3c-cc2080bca890","resolution":{"observed_at":"2026-08-06T17:33:55.927272Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T17:33:55.805680Z","title":"Dermatologist-level classification of skin cancer with deep neural networks","venue":null,"work_id":"cfe441b1-9bda-48f1-b733-a5952dd35efc","year":2017},"citing_paper":{"arxiv_id":"2507.10491","last_updated":"2025-07-14T17:13:06Z","snapshot_observed_at":"2026-08-10T20:21:34.860714Z","submitted_at":"2025-07-14T17:13:06Z","title":"BURN: Backdoor Unlearning via Adversarial Boundary Analysis","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T17:33:48.885427Z"},"links":{"citing_paper":"/paper/2507.10491"},"observation_digest":"sha256:870b432b52e979b763f48250507d5d6386cdf9bf381daa136cbb5349f4c3aaf4","observation_id":"651eaaae-6bf2-4741-9401-5a0f4fcf4368","resolution":{"observed_at":"2026-08-06T17:33:55.811085Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1708.06733","last_updated":"2019-03-11T20:45:33Z","snapshot_observed_at":"2026-08-12T15:43:59.037380Z","submitted_at":"2017-08-22T17:31:54Z","title":"BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1708.06733","snapshot_observed_at":"2026-08-06T17:33:49.039603Z","title":"Bad- nets: Identifying vulnerabilities in the machine learning model supply chain","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.10491","last_updated":"2025-07-14T17:13:06Z","snapshot_observed_at":"2026-08-10T20:21:34.860714Z","submitted_at":"2025-07-14T17:13:06Z","title":"BURN: Backdoor Unlearning via Adversarial Boundary Analysis","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T17:33:49.039603Z"},"links":{"cited_paper":"/paper/1708.06733","citing_paper":"/paper/2507.10491"},"observation_digest":"sha256:d0209ae9764f1db0fe6d9db926572cda0230563e119784d492008f4f657e3de2","observation_id":"40b5107f-703f-4c42-bb9a-2c8ec26950c4","resolution":{"observed_at":"2026-08-06T17:33:49.039603Z","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":"2026-08-06T17:33:55.792228Z","title":"Identity mappings in deep residual networks","venue":null,"work_id":"d8448318-4f0d-4923-809d-7d400db75c9a","year":2016},"citing_paper":{"arxiv_id":"2507.10491","last_updated":"2025-07-14T17:13:06Z","snapshot_observed_at":"2026-08-10T20:21:34.860714Z","submitted_at":"2025-07-14T17:13:06Z","title":"BURN: Backdoor Unlearning via Adversarial Boundary Analysis","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T17:33:49.220020Z"},"links":{"citing_paper":"/paper/2507.10491"},"observation_digest":"sha256:8904bd57a6984a51b04c034d83d61ec36a7d3b441f07336bf105bc35ddf12ab0","observation_id":"2b33d4fc-4dd1-4cc1-98e8-23840586146a","resolution":{"observed_at":"2026-08-06T17:33:55.795968Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2202.03423","last_updated":"2022-02-05T03:34:01Z","snapshot_observed_at":"2026-08-14T10:11:06.125442Z","submitted_at":"2022-02-05T03:34:01Z","title":"Backdoor Defense via Decoupling the Training Process","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.03423","snapshot_observed_at":"2026-08-06T17:33:49.387199Z","title":"Backdoor defense via decoupling the training process","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.10491","last_updated":"2025-07-14T17:13:06Z","snapshot_observed_at":"2026-08-10T20:21:34.860714Z","submitted_at":"2025-07-14T17:13:06Z","title":"BURN: Backdoor Unlearning via Adversarial Boundary Analysis","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T17:33:49.387199Z"},"links":{"cited_paper":"/paper/2202.03423","citing_paper":"/paper/2507.10491"},"observation_digest":"sha256:6f871fed8d3e6112e1b39d9bc0d38df876e61940b07d809897fe8aa250f37aa7","observation_id":"97c2c446-8782-4311-9505-6091ab84845d","resolution":{"observed_at":"2026-08-06T17:33:49.387199Z","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":"2026-08-06T17:33:49.508648Z","title":"Learning multiple layers of features from tiny images","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2507.10491","last_updated":"2025-07-14T17:13:06Z","snapshot_observed_at":"2026-08-10T20:21:34.860714Z","submitted_at":"2025-07-14T17:13:06Z","title":"BURN: Backdoor Unlearning via Adversarial Boundary Analysis","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T17:33:49.508648Z"},"links":{"citing_paper":"/paper/2507.10491"},"observation_digest":"sha256:5c721f14fd5dcd73735cae74ac8b5a54fab7d1b83c90712d05c12260354ae22d","observation_id":"435f5796-b775-41c5-bf91-283d984dc678","resolution":{"observed_at":"2026-08-06T17:33:49.508648Z","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":"2026-08-06T17:33:55.771606Z","title":"Invisible backdoor attack with sample-specific triggers","venue":null,"work_id":"25883a5a-8968-4e18-a595-1016b34f5c41","year":2021},"citing_paper":{"arxiv_id":"2507.10491","last_updated":"2025-07-14T17:13:06Z","snapshot_observed_at":"2026-08-10T20:21:34.860714Z","submitted_at":"2025-07-14T17:13:06Z","title":"BURN: Backdoor Unlearning via Adversarial Boundary Analysis","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T17:33:49.618490Z"},"links":{"citing_paper":"/paper/2507.10491"},"observation_digest":"sha256:fd357920b8e773fbe2ef2169e66e83d115013742ba538a3048bb9f32587962dd","observation_id":"d2cde874-5a0f-4ed4-ae4a-a197250163d4","resolution":{"observed_at":"2026-08-06T17:33:55.775497Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"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":"2026-08-06T17:33:49.807827Z","title":"Neural attention distillation: Erasing backdoor triggers from deep neural networks","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.10491","last_updated":"2025-07-14T17:13:06Z","snapshot_observed_at":"2026-08-10T20:21:34.860714Z","submitted_at":"2025-07-14T17:13:06Z","title":"BURN: Backdoor Unlearning via Adversarial Boundary Analysis","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T17:33:49.807827Z"},"links":{"cited_paper":"/paper/2101.05930","citing_paper":"/paper/2507.10491"},"observation_digest":"sha256:855e823eb97875f69998241b79d6f9d912bf72714af82f0cfefacdea8cb9d985","observation_id":"09d81821-9783-465e-a588-f927c20ee1df","resolution":{"observed_at":"2026-08-06T17:33:49.807827Z","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":"2026-08-06T17:33:55.758894Z","title":"Fine- pruning: Defending against backdooring attacks on deep neural networks","venue":null,"work_id":"e395d38f-bde6-486d-8d88-1ad97507d643","year":null},"citing_paper":{"arxiv_id":"2507.10491","last_updated":"2025-07-14T17:13:06Z","snapshot_observed_at":"2026-08-10T20:21:34.860714Z","submitted_at":"2025-07-14T17:13:06Z","title":"BURN: Backdoor Unlearning via Adversarial Boundary Analysis","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T17:33:49.946195Z"},"links":{"citing_paper":"/paper/2507.10491"},"observation_digest":"sha256:b3e5b6c211980e3e1d3e1e746af3145026fc44ba0f35da9231b45c5b8e2022f4","observation_id":"9a87a150-226b-499b-a806-852479a28445","resolution":{"observed_at":"2026-08-06T17:33:55.763688Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T17:33:55.746540Z","title":"Trojaning attack on neural networks","venue":null,"work_id":"3abe9054-2c5f-4f38-91ae-1992f9353da7","year":2018},"citing_paper":{"arxiv_id":"2507.10491","last_updated":"2025-07-14T17:13:06Z","snapshot_observed_at":"2026-08-10T20:21:34.860714Z","submitted_at":"2025-07-14T17:13:06Z","title":"BURN: Backdoor Unlearning via Adversarial Boundary Analysis","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T17:33:50.070529Z"},"links":{"citing_paper":"/paper/2507.10491"},"observation_digest":"sha256:6b8302e445f3c6e87bfb5c23261ec01de3ac85f34d8a017069f52330e5889394","observation_id":"89a81f6d-4891-428b-bd36-556607503750","resolution":{"observed_at":"2026-08-06T17:33:55.750371Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T17:33:55.734632Z","title":"Abs: Scanning neural networks for back-doors by artificial brain stimulation","venue":null,"work_id":"037c6236-14aa-4f5c-989a-1cceb091f846","year":2019},"citing_paper":{"arxiv_id":"2507.10491","last_updated":"2025-07-14T17:13:06Z","snapshot_observed_at":"2026-08-10T20:21:34.860714Z","submitted_at":"2025-07-14T17:13:06Z","title":"BURN: Backdoor Unlearning via Adversarial Boundary Analysis","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T17:33:50.267563Z"},"links":{"citing_paper":"/paper/2507.10491"},"observation_digest":"sha256:80c5a18f4d33f733946a319cb8bb2361b5e8c4ff3744713d1e887f2a24127c8f","observation_id":"b31639b8-4297-4ed7-8e28-0ecc7dcbbee1","resolution":{"observed_at":"2026-08-06T17:33:55.738446Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T17:33:55.721774Z","title":"Deepfool: a simple and accurate method to fool deep neural networks","venue":null,"work_id":"64cfe372-fa88-419e-a421-8cc9779d9890","year":2016},"citing_paper":{"arxiv_id":"2507.10491","last_updated":"2025-07-14T17:13:06Z","snapshot_observed_at":"2026-08-10T20:21:34.860714Z","submitted_at":"2025-07-14T17:13:06Z","title":"BURN: Backdoor Unlearning via Adversarial Boundary Analysis","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T17:33:50.499657Z"},"links":{"citing_paper":"/paper/2507.10491"},"observation_digest":"sha256:25fab6e4852b05790171ce1bef52197bb0d3d13d5cd943991a234d7395c4ee99","observation_id":"036b8f8c-05f2-44de-bc48-199d67e508e4","resolution":{"observed_at":"2026-08-06T17:33:55.725744Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T17:33:55.710157Z","title":"Progressive backdoor erasing via connecting backdoor and adversarial attacks","venue":null,"work_id":"fefe1239-7d92-4a45-a6cc-04fa296b88f2","year":2023},"citing_paper":{"arxiv_id":"2507.10491","last_updated":"2025-07-14T17:13:06Z","snapshot_observed_at":"2026-08-10T20:21:34.860714Z","submitted_at":"2025-07-14T17:13:06Z","title":"BURN: Backdoor Unlearning via Adversarial Boundary Analysis","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T17:33:50.653675Z"},"links":{"citing_paper":"/paper/2507.10491"},"observation_digest":"sha256:5979ee1aa823d6366cb6320bb2b0d499f61bce95d4a2b07275b28901e6b6d9e5","observation_id":"3eb1b591-ed82-45b0-9df8-fb99b99ffc86","resolution":{"observed_at":"2026-08-06T17:33:55.713830Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T17:33:55.697698Z","title":"Input-aware dynamic back- door attack","venue":null,"work_id":"4719e560-131a-45b5-933c-1e6fe5d70dbb","year":2020},"citing_paper":{"arxiv_id":"2507.10491","last_updated":"2025-07-14T17:13:06Z","snapshot_observed_at":"2026-08-10T20:21:34.860714Z","submitted_at":"2025-07-14T17:13:06Z","title":"BURN: Backdoor Unlearning via Adversarial Boundary Analysis","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T17:33:50.789948Z"},"links":{"citing_paper":"/paper/2507.10491"},"observation_digest":"sha256:990b18249ab019a8b03943607e1397ce4ce07eeb82872d39898feb66d67ec08c","observation_id":"58e706fe-d829-4585-89da-b19cc9c3458e","resolution":{"observed_at":"2026-08-06T17:33:55.701818Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T17:33:55.684548Z","title":"Deep face recognition","venue":null,"work_id":"bad05a62-a20a-4243-ab9d-16f4cf275f8c","year":2015},"citing_paper":{"arxiv_id":"2507.10491","last_updated":"2025-07-14T17:13:06Z","snapshot_observed_at":"2026-08-10T20:21:34.860714Z","submitted_at":"2025-07-14T17:13:06Z","title":"BURN: Backdoor Unlearning via Adversarial Boundary Analysis","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T17:33:50.905856Z"},"links":{"citing_paper":"/paper/2507.10491"},"observation_digest":"sha256:30ca64279d6b60feb7ae8216245b9d26b2211f98337c5ec22b6b5cde24b4d365","observation_id":"7c8b2cfb-2ea8-4a01-b409-3432a59c073b","resolution":{"observed_at":"2026-08-06T17:33:55.688750Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2308.15673","last_updated":"2023-09-03T01:59:49Z","snapshot_observed_at":"2026-08-13T10:24:35.927324Z","submitted_at":"2023-08-30T00:03:03Z","title":"MDTD: A Multi Domain Trojan Detector for Deep Neural Networks","version":2},"cited_work":{"arxiv_id":"2308.15673","doi":null,"metadata_source":"pith","pith_arxiv_id":"2308.15673","snapshot_observed_at":"2026-08-06T17:33:53.507801Z","title":"MDTD: A Multi Domain Trojan Detector for Deep Neural Networks","venue":"cs.CR","work_id":"d2eb6e40-1bc7-46ed-8aa7-dbed0b219add","year":2023},"citing_paper":{"arxiv_id":"2507.10491","last_updated":"2025-07-14T17:13:06Z","snapshot_observed_at":"2026-08-10T20:21:34.860714Z","submitted_at":"2025-07-14T17:13:06Z","title":"BURN: Backdoor Unlearning via Adversarial Boundary Analysis","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T17:33:51.020301Z"},"links":{"cited_paper":"/paper/2308.15673","citing_paper":"/paper/2507.10491"},"observation_digest":"sha256:5da9329bfab804e2c5b4bbd47d28610d34f75916cd0c363c0337dd8d7db27400","observation_id":"519b571f-c499-4fe4-8ba8-bd96ddfe5bff","resolution":{"observed_at":"2026-08-06T17:33:53.595000Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T17:33:55.672451Z","title":"You only look once: Unified, real-time object de- tection","venue":null,"work_id":"988f9444-df15-4a27-902a-2d5e96b12204","year":2016},"citing_paper":{"arxiv_id":"2507.10491","last_updated":"2025-07-14T17:13:06Z","snapshot_observed_at":"2026-08-10T20:21:34.860714Z","submitted_at":"2025-07-14T17:13:06Z","title":"BURN: Backdoor Unlearning via Adversarial Boundary Analysis","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T17:33:51.167127Z"},"links":{"citing_paper":"/paper/2507.10491"},"observation_digest":"sha256:e0df8b0b930e776a1ffd26c800d8a3124572809f258b5f41f010438c9e5f0853","observation_id":"bf34167e-77ae-49e5-8327-a69a68986a70","resolution":{"observed_at":"2026-08-06T17:33:55.676238Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T17:33:55.638913Z","title":"Universal backdoor attacks","venue":null,"work_id":"5a55ae5f-7214-4223-a580-1c0193ab4c44","year":2024},"citing_paper":{"arxiv_id":"2507.10491","last_updated":"2025-07-14T17:13:06Z","snapshot_observed_at":"2026-08-10T20:21:34.860714Z","submitted_at":"2025-07-14T17:13:06Z","title":"BURN: Backdoor Unlearning via Adversarial Boundary Analysis","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T17:33:51.302852Z"},"links":{"citing_paper":"/paper/2507.10491"},"observation_digest":"sha256:1de4d255a8bdaa15445927662c02bcecc83a60bef87efa52188e68a2c71195c2","observation_id":"b6122c3f-8a0b-4203-909e-6b128af8d073","resolution":{"observed_at":"2026-08-06T17:33:55.663915Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T17:33:55.542682Z","title":"Model x-ray: Detecting backdoored models via decision boundary","venue":null,"work_id":"89b1abb8-8bb6-4b8d-b931-ec1801ac09b3","year":2024},"citing_paper":{"arxiv_id":"2507.10491","last_updated":"2025-07-14T17:13:06Z","snapshot_observed_at":"2026-08-10T20:21:34.860714Z","submitted_at":"2025-07-14T17:13:06Z","title":"BURN: Backdoor Unlearning via Adversarial Boundary Analysis","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T17:33:51.451487Z"},"links":{"citing_paper":"/paper/2507.10491"},"observation_digest":"sha256:ee1dab26d8ea0d6eadc9a716bd999e6b10bb87b8c446156527cc2b97180b953f","observation_id":"6e4c47e5-d67d-42c1-a757-11b3a28d145f","resolution":{"observed_at":"2026-08-06T17:33:55.627196Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1912.02771","last_updated":"2019-12-06T23:16:45Z","snapshot_observed_at":"2026-08-10T18:11:31.253134Z","submitted_at":"2019-12-05T18:05:59Z","title":"Label-Consistent Backdoor Attacks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1912.02771","snapshot_observed_at":"2026-08-06T17:33:51.578940Z","title":"Label-consistent backdoor attacks","venue":null,"work_id":null,"year":1912},"citing_paper":{"arxiv_id":"2507.10491","last_updated":"2025-07-14T17:13:06Z","snapshot_observed_at":"2026-08-10T20:21:34.860714Z","submitted_at":"2025-07-14T17:13:06Z","title":"BURN: Backdoor Unlearning via Adversarial Boundary Analysis","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T17:33:51.578940Z"},"links":{"cited_paper":"/paper/1912.02771","citing_paper":"/paper/2507.10491"},"observation_digest":"sha256:fd7d7a96bdd871e8d21b188cb5ae371f8138f33bfdbcb2f091e40d2a5335943c","observation_id":"52371684-3e19-4543-8f27-7295932f9c19","resolution":{"observed_at":"2026-08-06T17:33:51.578940Z","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":"2026-08-06T17:33:55.390859Z","title":"Neural cleanse: Identifying and mitigating backdoor attacks in neural net- works","venue":null,"work_id":"71f76791-e9d9-4c31-a932-3d094147800c","year":2019},"citing_paper":{"arxiv_id":"2507.10491","last_updated":"2025-07-14T17:13:06Z","snapshot_observed_at":"2026-08-10T20:21:34.860714Z","submitted_at":"2025-07-14T17:13:06Z","title":"BURN: Backdoor Unlearning via Adversarial Boundary Analysis","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T17:33:51.679878Z"},"links":{"citing_paper":"/paper/2507.10491"},"observation_digest":"sha256:f89a5416e13a49a968b0fffb02420a71333d0c8b3f5ca60f6a337ff8762426a3","observation_id":"c365a357-1c99-4bd2-a5d4-e150d8911212","resolution":{"observed_at":"2026-08-06T17:33:55.463645Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T17:33:55.190492Z","title":"Bppattack: Stealthy and efficient trojan attacks against deep neural net- works via image quantization and contrastive adversarial learning","venue":null,"work_id":"10e659ad-cff3-4e68-a3f3-2435f1510af7","year":2022},"citing_paper":{"arxiv_id":"2507.10491","last_updated":"2025-07-14T17:13:06Z","snapshot_observed_at":"2026-08-10T20:21:34.860714Z","submitted_at":"2025-07-14T17:13:06Z","title":"BURN: Backdoor Unlearning via Adversarial Boundary Analysis","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T17:33:51.888686Z"},"links":{"citing_paper":"/paper/2507.10491"},"observation_digest":"sha256:7667e93f52b8f59c1fd9b4585c92ee733d6a8d28280e067957afa4c036c1d8ab","observation_id":"18eb872c-e02d-4c6d-8013-02dfd9b148c0","resolution":{"observed_at":"2026-08-06T17:33:55.266130Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T17:33:54.995421Z","title":"Shared adversarial unlearning: Backdoor mitigation by unlearning shared adversarial examples","venue":null,"work_id":"1fabbaaf-8313-4c8c-834a-1aeddc1e41ae","year":2023},"citing_paper":{"arxiv_id":"2507.10491","last_updated":"2025-07-14T17:13:06Z","snapshot_observed_at":"2026-08-10T20:21:34.860714Z","submitted_at":"2025-07-14T17:13:06Z","title":"BURN: Backdoor Unlearning via Adversarial Boundary Analysis","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T17:33:52.104328Z"},"links":{"citing_paper":"/paper/2507.10491"},"observation_digest":"sha256:e1215489289578f0e0de78bfc425ae843bc7fa77e3cc1b36d3190bb23a23b4ab","observation_id":"a137bcd9-2ab6-4c64-9072-0cb2e670ec9f","resolution":{"observed_at":"2026-08-06T17:33:55.072373Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T17:33:54.781961Z","title":"Backdoorbench: A comprehensive benchmark of backdoor learning","venue":null,"work_id":"0f0773ae-473b-452e-af6b-3e534ea632ce","year":null},"citing_paper":{"arxiv_id":"2507.10491","last_updated":"2025-07-14T17:13:06Z","snapshot_observed_at":"2026-08-10T20:21:34.860714Z","submitted_at":"2025-07-14T17:13:06Z","title":"BURN: Backdoor Unlearning via Adversarial Boundary Analysis","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T17:33:52.281972Z"},"links":{"citing_paper":"/paper/2507.10491"},"observation_digest":"sha256:d388b795c7e7a3eaacdc4ea18b1f0a0047c53bb7345a9d84dfbb9d3c4dde0050","observation_id":"9d13d241-3a06-4b7f-9852-25de9e4931b7","resolution":{"observed_at":"2026-08-06T17:33:54.883878Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T17:33:54.599508Z","title":"Adversarial neuron prun- ing purifies backdoored deep models","venue":null,"work_id":"8d9123b3-0e08-4dd0-970a-1692506e5780","year":2021},"citing_paper":{"arxiv_id":"2507.10491","last_updated":"2025-07-14T17:13:06Z","snapshot_observed_at":"2026-08-10T20:21:34.860714Z","submitted_at":"2025-07-14T17:13:06Z","title":"BURN: Backdoor Unlearning via Adversarial Boundary Analysis","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T17:33:52.464395Z"},"links":{"citing_paper":"/paper/2507.10491"},"observation_digest":"sha256:3ed25440098e983f01bd33c56fd756f53e519561f04f55de342c68b47973a001","observation_id":"95d67ba4-1fcc-4322-90ba-b4bfc10ced2c","resolution":{"observed_at":"2026-08-06T17:33:54.680626Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T17:33:54.345024Z","title":"Cbd: A certified back- door detector based on local dominant probability","venue":null,"work_id":"be3b773e-4df0-4617-a107-5e76564360fe","year":2024},"citing_paper":{"arxiv_id":"2507.10491","last_updated":"2025-07-14T17:13:06Z","snapshot_observed_at":"2026-08-10T20:21:34.860714Z","submitted_at":"2025-07-14T17:13:06Z","title":"BURN: Backdoor Unlearning via Adversarial Boundary Analysis","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T17:33:52.631175Z"},"links":{"citing_paper":"/paper/2507.10491"},"observation_digest":"sha256:ef2f9a530f6cc7bc01f9a9f4841b58d14a52453b114dea6327e3ccc93f71e2b4","observation_id":"504b98d9-d897-4c9f-a353-a9c0b378ce7f","resolution":{"observed_at":"2026-08-06T17:33:54.470676Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2110.03735","last_updated":"2022-02-06T21:26:28Z","snapshot_observed_at":"2026-08-15T07:14:48.493848Z","submitted_at":"2021-10-07T18:32:54Z","title":"Adversarial Unlearning of Backdoors via Implicit Hypergradient","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.03735","snapshot_observed_at":"2026-08-06T17:33:52.804575Z","title":"Adversarial unlearning of backdoors via implicit hypergradient","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.10491","last_updated":"2025-07-14T17:13:06Z","snapshot_observed_at":"2026-08-10T20:21:34.860714Z","submitted_at":"2025-07-14T17:13:06Z","title":"BURN: Backdoor Unlearning via Adversarial Boundary Analysis","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-06T17:33:52.804575Z"},"links":{"cited_paper":"/paper/2110.03735","citing_paper":"/paper/2507.10491"},"observation_digest":"sha256:7a968dae3ae33e5b7cdfb617c89fd425a40afb82d437c4425e447dc5676402f5","observation_id":"c112a32a-9fff-4865-955a-8573fb044fe0","resolution":{"observed_at":"2026-08-06T17:33:52.804575Z","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":"2026-08-06T17:33:54.096393Z","title":"Re- thinking the backdoor attacks’ triggers: A frequency per- spective","venue":null,"work_id":"39f9fcda-5dc0-4825-a082-34427ad1e1e2","year":2021},"citing_paper":{"arxiv_id":"2507.10491","last_updated":"2025-07-14T17:13:06Z","snapshot_observed_at":"2026-08-10T20:21:34.860714Z","submitted_at":"2025-07-14T17:13:06Z","title":"BURN: Backdoor Unlearning via Adversarial Boundary Analysis","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-06T17:33:52.980657Z"},"links":{"citing_paper":"/paper/2507.10491"},"observation_digest":"sha256:dc84d22849deed22d7bb5e1881bc42b7e1e99ea3841147f276cb9bfb997daf92","observation_id":"c06b8b86-824c-49e2-a676-4228aaef1a34","resolution":{"observed_at":"2026-08-06T17:33:54.207373Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T17:33:53.911589Z","title":"Poison ink: Robust and invisible backdoor attack","venue":null,"work_id":"ce0d814a-5e2e-4fb3-914c-2ecc6ae7b5ab","year":2022},"citing_paper":{"arxiv_id":"2507.10491","last_updated":"2025-07-14T17:13:06Z","snapshot_observed_at":"2026-08-10T20:21:34.860714Z","submitted_at":"2025-07-14T17:13:06Z","title":"BURN: Backdoor Unlearning via Adversarial Boundary Analysis","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-06T17:33:53.169511Z"},"links":{"citing_paper":"/paper/2507.10491"},"observation_digest":"sha256:71281fd673fada7910fa60170bc73ffbe980183739440e76ce5555d206c7f1c0","observation_id":"024f1b48-d532-4eb8-93de-be88633febb3","resolution":{"observed_at":"2026-08-06T17:33:53.979510Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T17:33:53.742838Z","title":"Enhancing fine-tuning based backdoor defense with sharpness-aware minimization","venue":null,"work_id":"dd197feb-edda-4842-887f-74c1aa8ee3c7","year":2023},"citing_paper":{"arxiv_id":"2507.10491","last_updated":"2025-07-14T17:13:06Z","snapshot_observed_at":"2026-08-10T20:21:34.860714Z","submitted_at":"2025-07-14T17:13:06Z","title":"BURN: Backdoor Unlearning via Adversarial Boundary Analysis","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-06T17:33:53.329238Z"},"links":{"citing_paper":"/paper/2507.10491"},"observation_digest":"sha256:7a35d89dfe6252c927dce6a597cc4bf2379ae60fd3eeeac29cc247c70a0b9c4c","observation_id":"ccd8d356-65cc-412b-8fc6-2b8c951ed8cf","resolution":{"observed_at":"2026-08-06T17:33:53.839880Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2507.10491","last_updated":"2025-07-14T17:13:06Z","latest_version":1,"primary_category":"cs.CR","snapshot_observed_at":"2026-08-10T20:21:34.860714Z","submitted_at":"2025-07-14T17:13:06Z","title":"BURN: Backdoor Unlearning via Adversarial Boundary Analysis"},"reference_resolution":{"displayed":34,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":8,"verified_exact":1,"verified_fuzzy":25},"total_outbound_references":34},"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":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"thesis":"As of 15 August 2026, this Paper Citation Record lists 34 of 34 outbound references and 0 inbound Pith citation observations for arXiv:2507.10491."}