{"as_of":"2026-08-08T14:55:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:08243668115e7d66e87d96ba95d7c4a99b16bc9bc52e12f732eea280de0383fd","coverage":[{"denominator":49,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":49,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T04:24:22.959017Z","state":"measured"},{"denominator":49,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":49,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+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/2506.10722/citation-record","integrity":"/paper/2506.10722/integrity","json":"/paper/2506.10722/citation-record.json","paper":"/paper/2506.10722"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T04:24:28.190092Z","title":"Deep learning for 3d point clouds: A survey,","venue":null,"work_id":"9ec7adfd-e44a-4e8f-85db-7e4505d108f0","year":2021},"citing_paper":{"arxiv_id":"2506.10722","last_updated":"2025-06-12T14:12:15Z","snapshot_observed_at":"2026-08-07T04:17:18.839831Z","submitted_at":"2025-06-12T14:12:15Z","title":"TED-LaST: Towards Robust Backdoor Defense Against Adaptive Attacks","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T04:24:19.284278Z"},"links":{"citing_paper":"/paper/2506.10722"},"observation_digest":"sha256:997c784ecb6b2d0f4fc94de9c8ebc5a5f70d81624dd7efc447841b17b0e10ca7","observation_id":"49b92c28-f98e-46d9-8da8-df81fc4645bd","resolution":{"observed_at":"2026-08-07T04:24:28.192664Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T04:24:28.181605Z","title":"Deep audio-visual speech recognition,","venue":null,"work_id":"b92cf212-8dc1-4d05-84f8-2e041c730c4f","year":2022},"citing_paper":{"arxiv_id":"2506.10722","last_updated":"2025-06-12T14:12:15Z","snapshot_observed_at":"2026-08-07T04:17:18.839831Z","submitted_at":"2025-06-12T14:12:15Z","title":"TED-LaST: Towards Robust Backdoor Defense Against Adaptive Attacks","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T04:24:19.354694Z"},"links":{"citing_paper":"/paper/2506.10722"},"observation_digest":"sha256:86c9f655502736bfb425da539678a8e690fa5a1e924b9554187f038f665001d1","observation_id":"eeeb4730-2085-44ef-80fa-0ac4a03a3d18","resolution":{"observed_at":"2026-08-07T04:24:28.184417Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T04:24:28.173416Z","title":"From handcrafted to deep features for pedestrian detection: A survey,","venue":null,"work_id":"648f9dd8-1077-4992-ba78-c463484eb581","year":2022},"citing_paper":{"arxiv_id":"2506.10722","last_updated":"2025-06-12T14:12:15Z","snapshot_observed_at":"2026-08-07T04:17:18.839831Z","submitted_at":"2025-06-12T14:12:15Z","title":"TED-LaST: Towards Robust Backdoor Defense Against Adaptive Attacks","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T04:24:19.443949Z"},"links":{"citing_paper":"/paper/2506.10722"},"observation_digest":"sha256:ca39c36d729178c4ae8c9ad6eb07a517a8c3e46add062a983c20b3f0615e2816","observation_id":"1726f2b8-9a0c-40e1-a7ac-6ec4dd8856f5","resolution":{"observed_at":"2026-08-07T04:24:28.176520Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1708.06733","last_updated":"2019-03-11T20:45:33Z","snapshot_observed_at":"2026-07-06T05:56:16.413472Z","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":"2026-08-07T04:24:19.509666Z","title":"Badnets: Identifying vulnerabilities in the machine learning model supply chain,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.10722","last_updated":"2025-06-12T14:12:15Z","snapshot_observed_at":"2026-08-07T04:17:18.839831Z","submitted_at":"2025-06-12T14:12:15Z","title":"TED-LaST: Towards Robust Backdoor Defense Against Adaptive Attacks","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T04:24:19.509666Z"},"links":{"cited_paper":"/paper/1708.06733","citing_paper":"/paper/2506.10722"},"observation_digest":"sha256:a3b1d7b99be05e7e18e7b69f4a20c7764a1c5eff6f9beb2cf2f9e1d19986f7cb","observation_id":"ee5132e4-972c-459b-bf2d-4196f474c1c4","resolution":{"observed_at":"2026-08-07T04:24:19.509666Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2108.13888","last_updated":"2021-08-31T14:47:37Z","snapshot_observed_at":"2026-07-06T11:43:05.180555Z","submitted_at":"2021-08-31T14:47:37Z","title":"Backdoor Attacks on Pre-trained Models by Layerwise Weight Poisoning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2108.13888","snapshot_observed_at":"2026-08-07T04:24:19.603959Z","title":"Backdoor attacks on pre-trained models by layerwise weight poisoning,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.10722","last_updated":"2025-06-12T14:12:15Z","snapshot_observed_at":"2026-08-07T04:17:18.839831Z","submitted_at":"2025-06-12T14:12:15Z","title":"TED-LaST: Towards Robust Backdoor Defense Against Adaptive Attacks","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T04:24:19.603959Z"},"links":{"cited_paper":"/paper/2108.13888","citing_paper":"/paper/2506.10722"},"observation_digest":"sha256:a9a9cfbb7a762e7289af1a785056ee565a678449b0c4b53e308d7436fa8552fa","observation_id":"36bfeaeb-b615-49ea-8bc5-d528e25a45fa","resolution":{"observed_at":"2026-08-07T04:24:19.603959Z","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":"2026-08-07T04:24:28.165653Z","title":"Trojaning attack on neural networks,","venue":null,"work_id":"78bf64e0-f378-49b3-b66e-00930fac9114","year":2018},"citing_paper":{"arxiv_id":"2506.10722","last_updated":"2025-06-12T14:12:15Z","snapshot_observed_at":"2026-08-07T04:17:18.839831Z","submitted_at":"2025-06-12T14:12:15Z","title":"TED-LaST: Towards Robust Backdoor Defense Against Adaptive Attacks","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T04:24:19.677321Z"},"links":{"citing_paper":"/paper/2506.10722"},"observation_digest":"sha256:6530133d5fb060cae1b264d96db63e7a646c4cc510c06fff37ff8d5524fe5844","observation_id":"5a3493f1-26eb-45d6-86f2-6ada1d166251","resolution":{"observed_at":"2026-08-07T04:24:28.168293Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T04:24:28.158023Z","title":"Be careful about poisoned word embeddings: Exploring the vulnerability of the embedding layers in NLP models,","venue":null,"work_id":"5561874b-7ae1-4a92-93cc-98af11a60d21","year":2021},"citing_paper":{"arxiv_id":"2506.10722","last_updated":"2025-06-12T14:12:15Z","snapshot_observed_at":"2026-08-07T04:17:18.839831Z","submitted_at":"2025-06-12T14:12:15Z","title":"TED-LaST: Towards Robust Backdoor Defense Against Adaptive Attacks","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T04:24:19.774606Z"},"links":{"citing_paper":"/paper/2506.10722"},"observation_digest":"sha256:8010ecc9c2a26d5abb4eba113d3590b6fe21dad01049571f8fb489e6307f260e","observation_id":"ad3b7e31-5e1b-410c-9ba9-7e88df626af3","resolution":{"observed_at":"2026-08-07T04:24:28.160705Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T04:24:28.149833Z","title":"Turning your weakness into a strength: Watermarking deep neural net- works by backdooring,","venue":null,"work_id":"393affa6-5d30-40c6-98b5-d1cbaf417e7b","year":2018},"citing_paper":{"arxiv_id":"2506.10722","last_updated":"2025-06-12T14:12:15Z","snapshot_observed_at":"2026-08-07T04:17:18.839831Z","submitted_at":"2025-06-12T14:12:15Z","title":"TED-LaST: Towards Robust Backdoor Defense Against Adaptive Attacks","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T04:24:19.883911Z"},"links":{"citing_paper":"/paper/2506.10722"},"observation_digest":"sha256:8a90aa550a530869412da91beb79db266f86831982424924fe331f5535e0af9c","observation_id":"c5e1fe31-c13b-4582-87b8-9dd3cc6c558f","resolution":{"observed_at":"2026-08-07T04:24:28.152590Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T04:24:28.142225Z","title":"Composite backdoor attack for deep neural network by mixing existing benign features,","venue":null,"work_id":"0e0beaa6-dd3e-4796-bc36-1e8340a5d136","year":2020},"citing_paper":{"arxiv_id":"2506.10722","last_updated":"2025-06-12T14:12:15Z","snapshot_observed_at":"2026-08-07T04:17:18.839831Z","submitted_at":"2025-06-12T14:12:15Z","title":"TED-LaST: Towards Robust Backdoor Defense Against Adaptive Attacks","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T04:24:19.965605Z"},"links":{"citing_paper":"/paper/2506.10722"},"observation_digest":"sha256:17623687f9fdc75746abbd0f2442a407532d83821bd86da235d7db9d8833d476","observation_id":"7bed1f34-0cb6-49bb-924c-01518a6e1807","resolution":{"observed_at":"2026-08-07T04:24:28.144859Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T04:24:28.134031Z","title":"Demon in the variant: Statistical analysis of dnns for robust backdoor con- tamination detection","venue":null,"work_id":"2d3a5627-9513-46a2-844c-cddd3dc52c59","year":2021},"citing_paper":{"arxiv_id":"2506.10722","last_updated":"2025-06-12T14:12:15Z","snapshot_observed_at":"2026-08-07T04:17:18.839831Z","submitted_at":"2025-06-12T14:12:15Z","title":"TED-LaST: Towards Robust Backdoor Defense Against Adaptive Attacks","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T04:24:20.053292Z"},"links":{"citing_paper":"/paper/2506.10722"},"observation_digest":"sha256:9c68e92b91f36dc9435a06e59ddf97b892938fb079eef41fc1bf1dc22a0301ad","observation_id":"d92956bc-e211-4861-847b-5e76525f8099","resolution":{"observed_at":"2026-08-07T04:24:28.136802Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T04:24:20.124030Z","title":"Targeted backdoor attacks on deep learning systems using data poisoning,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.10722","last_updated":"2025-06-12T14:12:15Z","snapshot_observed_at":"2026-08-07T04:17:18.839831Z","submitted_at":"2025-06-12T14:12:15Z","title":"TED-LaST: Towards Robust Backdoor Defense Against Adaptive Attacks","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T04:24:20.124030Z"},"links":{"cited_paper":"/paper/1712.05526","citing_paper":"/paper/2506.10722"},"observation_digest":"sha256:a1efcb87f86b23e4aebcb8be21a21299663a8748a2dcf43b7853c36d29f801c7","observation_id":"e1a77684-9843-4fcc-83dc-88ebc9d09210","resolution":{"observed_at":"2026-08-07T04:24:20.124030Z","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":"2026-08-07T04:24:28.125552Z","title":"Rethinking the back- door attacks’ triggers: A frequency perspective,","venue":null,"work_id":"9e54d502-2171-4f19-b4fd-3fea6bad636b","year":2021},"citing_paper":{"arxiv_id":"2506.10722","last_updated":"2025-06-12T14:12:15Z","snapshot_observed_at":"2026-08-07T04:17:18.839831Z","submitted_at":"2025-06-12T14:12:15Z","title":"TED-LaST: Towards Robust Backdoor Defense Against Adaptive Attacks","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T04:24:20.191661Z"},"links":{"citing_paper":"/paper/2506.10722"},"observation_digest":"sha256:b3b78ad562d6d91fb5f02953dba0917c520d68384d41b3f650045199749d8a27","observation_id":"084e4b8f-23ca-4a6d-a7b2-058be7845348","resolution":{"observed_at":"2026-08-07T04:24:28.128719Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T04:24:28.116558Z","title":"Backdooring and poisoning neural networks with image-scaling attacks,","venue":null,"work_id":"629ece99-e58f-4f93-87aa-b2fa274b8b45","year":2020},"citing_paper":{"arxiv_id":"2506.10722","last_updated":"2025-06-12T14:12:15Z","snapshot_observed_at":"2026-08-07T04:17:18.839831Z","submitted_at":"2025-06-12T14:12:15Z","title":"TED-LaST: Towards Robust Backdoor Defense Against Adaptive Attacks","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T04:24:20.256199Z"},"links":{"citing_paper":"/paper/2506.10722"},"observation_digest":"sha256:3e43f1362f24b9a3756f6dc42f6bda4a827935cdeb6452bfb73b7488833805b8","observation_id":"7d5af119-f2f8-48cb-9ce9-d92e96aaa4be","resolution":{"observed_at":"2026-08-07T04:24:28.120196Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T04:24:27.997706Z","title":"Input-aware dynamic backdoor attack,","venue":null,"work_id":"cccbef83-689c-4fe7-9d7d-fc97774456be","year":2020},"citing_paper":{"arxiv_id":"2506.10722","last_updated":"2025-06-12T14:12:15Z","snapshot_observed_at":"2026-08-07T04:17:18.839831Z","submitted_at":"2025-06-12T14:12:15Z","title":"TED-LaST: Towards Robust Backdoor Defense Against Adaptive Attacks","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T04:24:20.299981Z"},"links":{"citing_paper":"/paper/2506.10722"},"observation_digest":"sha256:7c36b868e6adb0ce5a8aec1be1f6f2d637d2bf0bfc548fe7352bc8ed0d9bb39b","observation_id":"501f174c-4a01-4299-8f13-6e3d9b901ad7","resolution":{"observed_at":"2026-08-07T04:24:28.104190Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T04:24:27.792782Z","title":"Invisible backdoor attack with sample-specific triggers,","venue":null,"work_id":"7daf80e2-e555-46a6-8209-3951c30c1846","year":2021},"citing_paper":{"arxiv_id":"2506.10722","last_updated":"2025-06-12T14:12:15Z","snapshot_observed_at":"2026-08-07T04:17:18.839831Z","submitted_at":"2025-06-12T14:12:15Z","title":"TED-LaST: Towards Robust Backdoor Defense Against Adaptive Attacks","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T04:24:20.369307Z"},"links":{"citing_paper":"/paper/2506.10722"},"observation_digest":"sha256:20de2fb53651dba5b2370f86f327e1465bc931c0963151824c20a22ac9f26388","observation_id":"933880e6-5850-4ce7-80b0-6b23e1b98d30","resolution":{"observed_at":"2026-08-07T04:24:27.901901Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T04:24:27.598904Z","title":"Condi- tional backdoor attack via jpeg compression,","venue":null,"work_id":"25082a78-4e51-497b-9fbf-d627141a85f0","year":2024},"citing_paper":{"arxiv_id":"2506.10722","last_updated":"2025-06-12T14:12:15Z","snapshot_observed_at":"2026-08-07T04:17:18.839831Z","submitted_at":"2025-06-12T14:12:15Z","title":"TED-LaST: Towards Robust Backdoor Defense Against Adaptive Attacks","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T04:24:20.434671Z"},"links":{"citing_paper":"/paper/2506.10722"},"observation_digest":"sha256:cc9232b04743b73536c4d9c10b39f3c64991f08fd71de8ff805ee1f44addb02c","observation_id":"13b555e0-4f54-4fde-b9ad-dabaab899658","resolution":{"observed_at":"2026-08-07T04:24:27.728222Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T04:24:27.445930Z","title":"Backdoor attack on deep neural networks in perception domain,","venue":null,"work_id":"8e8c3b7f-fb6d-4441-a16e-c6a0c211415b","year":2023},"citing_paper":{"arxiv_id":"2506.10722","last_updated":"2025-06-12T14:12:15Z","snapshot_observed_at":"2026-08-07T04:17:18.839831Z","submitted_at":"2025-06-12T14:12:15Z","title":"TED-LaST: Towards Robust Backdoor Defense Against Adaptive Attacks","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T04:24:20.521848Z"},"links":{"citing_paper":"/paper/2506.10722"},"observation_digest":"sha256:5c4f55d6390c4480b01643e2f069e70d47c6013e42a1d2403d94c95470fbac7c","observation_id":"2e8c53f3-04ab-4597-bedb-c2ff99780c6c","resolution":{"observed_at":"2026-08-07T04:24:27.489548Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T04:24:27.281844Z","title":"Influence- driven data poisoning for robust recommender systems,","venue":null,"work_id":"b2c1dc14-39a9-449d-bc02-4194252f83f3","year":2023},"citing_paper":{"arxiv_id":"2506.10722","last_updated":"2025-06-12T14:12:15Z","snapshot_observed_at":"2026-08-07T04:17:18.839831Z","submitted_at":"2025-06-12T14:12:15Z","title":"TED-LaST: Towards Robust Backdoor Defense Against Adaptive Attacks","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T04:24:20.636837Z"},"links":{"citing_paper":"/paper/2506.10722"},"observation_digest":"sha256:b5dbfb252d1a0c5c2b0badc1c2f1032e42eb33d2bb04698f2a8c1df092f43037","observation_id":"20ddc3a6-f79f-4884-b099-e7d1d17ecd2a","resolution":{"observed_at":"2026-08-07T04:24:27.342250Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T04:24:27.048440Z","title":"Poisoning attack against estimating from pairwise comparisons,","venue":null,"work_id":"3d1ddb1e-f286-4b25-8ef7-b6ca2b704936","year":2022},"citing_paper":{"arxiv_id":"2506.10722","last_updated":"2025-06-12T14:12:15Z","snapshot_observed_at":"2026-08-07T04:17:18.839831Z","submitted_at":"2025-06-12T14:12:15Z","title":"TED-LaST: Towards Robust Backdoor Defense Against Adaptive Attacks","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T04:24:20.703392Z"},"links":{"citing_paper":"/paper/2506.10722"},"observation_digest":"sha256:e55cd5b3aace689311d513c4a3c55824130fb9024ebfb9f5a60e6939c3909bea","observation_id":"cf200b9d-fddf-451b-9602-7ca1e5fa67ef","resolution":{"observed_at":"2026-08-07T04:24:27.146050Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T04:24:26.968891Z","title":"Detecting ai trojans using meta neural analysis,","venue":null,"work_id":"002e8de3-4b0d-4497-a253-ca667671d918","year":2021},"citing_paper":{"arxiv_id":"2506.10722","last_updated":"2025-06-12T14:12:15Z","snapshot_observed_at":"2026-08-07T04:17:18.839831Z","submitted_at":"2025-06-12T14:12:15Z","title":"TED-LaST: Towards Robust Backdoor Defense Against Adaptive Attacks","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T04:24:20.785623Z"},"links":{"citing_paper":"/paper/2506.10722"},"observation_digest":"sha256:41ef96a7fd8533be719dced6ab777ca7f0fff1a45fa34382b88e8cd077a688a5","observation_id":"e85f855f-6e5d-441a-a963-58ca07b2f77d","resolution":{"observed_at":"2026-08-07T04:24:27.030261Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T04:24:26.849474Z","title":"Abs: Scanning neural networks for back-doors by artificial brain stimulation,","venue":null,"work_id":"dc619330-a015-48e5-b178-7571be610598","year":2019},"citing_paper":{"arxiv_id":"2506.10722","last_updated":"2025-06-12T14:12:15Z","snapshot_observed_at":"2026-08-07T04:17:18.839831Z","submitted_at":"2025-06-12T14:12:15Z","title":"TED-LaST: Towards Robust Backdoor Defense Against Adaptive Attacks","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T04:24:20.849525Z"},"links":{"citing_paper":"/paper/2506.10722"},"observation_digest":"sha256:bbb0d6d673661035de3838d44d8a83e425e8de978677769a7efe7659efbc4430","observation_id":"507a7b7c-0205-4422-b3c6-eba5402abeb6","resolution":{"observed_at":"2026-08-07T04:24:26.913280Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T04:24:26.693301Z","title":"Neural cleanse: Identifying and mitigating backdoor attacks in neural networks,","venue":null,"work_id":"117c7a88-1109-4e3c-aa91-51c28ff8dee7","year":2019},"citing_paper":{"arxiv_id":"2506.10722","last_updated":"2025-06-12T14:12:15Z","snapshot_observed_at":"2026-08-07T04:17:18.839831Z","submitted_at":"2025-06-12T14:12:15Z","title":"TED-LaST: Towards Robust Backdoor Defense Against Adaptive Attacks","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T04:24:20.940101Z"},"links":{"citing_paper":"/paper/2506.10722"},"observation_digest":"sha256:c0c6ac6826de92d4d5cd92c509525bf432d3de75b8c3228d22ffea14f06ff8a9","observation_id":"45405262-0559-48e0-987b-cb3a4c121ee2","resolution":{"observed_at":"2026-08-07T04:24:26.768664Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T04:24:26.515264Z","title":"Universal detection of backdoor attacks via density-based clustering and centroids analysis,","venue":null,"work_id":"f75b1251-6533-4696-a44e-589b3543eb99","year":2023},"citing_paper":{"arxiv_id":"2506.10722","last_updated":"2025-06-12T14:12:15Z","snapshot_observed_at":"2026-08-07T04:17:18.839831Z","submitted_at":"2025-06-12T14:12:15Z","title":"TED-LaST: Towards Robust Backdoor Defense Against Adaptive Attacks","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T04:24:20.991899Z"},"links":{"citing_paper":"/paper/2506.10722"},"observation_digest":"sha256:b4d02e3a7f6bb3bea2b8fcb6c521165f82f5abd0f761486455d00e8ea1eef58c","observation_id":"32d0c21e-3c16-4231-bb66-ea729429b76a","resolution":{"observed_at":"2026-08-07T04:24:26.600678Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T04:24:26.331077Z","title":"Neuralsanitizer: Detecting backdoors in neural networks,","venue":null,"work_id":"4e13a736-9684-48ad-a512-c8d3330805d1","year":2024},"citing_paper":{"arxiv_id":"2506.10722","last_updated":"2025-06-12T14:12:15Z","snapshot_observed_at":"2026-08-07T04:17:18.839831Z","submitted_at":"2025-06-12T14:12:15Z","title":"TED-LaST: Towards Robust Backdoor Defense Against Adaptive Attacks","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T04:24:21.062746Z"},"links":{"citing_paper":"/paper/2506.10722"},"observation_digest":"sha256:a9f2fb9f3129f037ba061800276a95325a2150c1e05f89f5b1c34ae440133e2a","observation_id":"11638299-0fd4-4e6b-b2f0-ba086ed269ac","resolution":{"observed_at":"2026-08-07T04:24:26.423134Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T04:24:26.180617Z","title":"Spectral signatures in backdoor attacks,","venue":null,"work_id":"242e8587-ab52-4a77-8290-868dfea42441","year":2018},"citing_paper":{"arxiv_id":"2506.10722","last_updated":"2025-06-12T14:12:15Z","snapshot_observed_at":"2026-08-07T04:17:18.839831Z","submitted_at":"2025-06-12T14:12:15Z","title":"TED-LaST: Towards Robust Backdoor Defense Against Adaptive Attacks","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T04:24:21.142836Z"},"links":{"citing_paper":"/paper/2506.10722"},"observation_digest":"sha256:40dd6c971c0ca8d181f75fada0285bea77bdc01f99eed5890437125abd2cbf34","observation_id":"52866111-06db-4dcd-8029-e1535300c5fe","resolution":{"observed_at":"2026-08-07T04:24:26.268265Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T04:24:26.028940Z","title":"Strip: A defence against trojan attacks on deep neural networks,","venue":null,"work_id":"844b5dcb-2ee5-41d1-810b-b25111b7008b","year":2019},"citing_paper":{"arxiv_id":"2506.10722","last_updated":"2025-06-12T14:12:15Z","snapshot_observed_at":"2026-08-07T04:17:18.839831Z","submitted_at":"2025-06-12T14:12:15Z","title":"TED-LaST: Towards Robust Backdoor Defense Against Adaptive Attacks","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T04:24:21.217161Z"},"links":{"citing_paper":"/paper/2506.10722"},"observation_digest":"sha256:eba43d8d8b20da788d89c9a950b4803917e8e39fb7f239a762e83a508b2a88ae","observation_id":"37f831e8-ee70-454b-bc6b-b8cc32a0276b","resolution":{"observed_at":"2026-08-07T04:24:26.116352Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T04:24:25.873125Z","title":"Detecting backdoors during the inference stage based on corruption robustness consistency,","venue":null,"work_id":"e2e54942-411c-4b73-ad5d-8300b5d51f25","year":2023},"citing_paper":{"arxiv_id":"2506.10722","last_updated":"2025-06-12T14:12:15Z","snapshot_observed_at":"2026-08-07T04:17:18.839831Z","submitted_at":"2025-06-12T14:12:15Z","title":"TED-LaST: Towards Robust Backdoor Defense Against Adaptive Attacks","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T04:24:21.288869Z"},"links":{"citing_paper":"/paper/2506.10722"},"observation_digest":"sha256:87aa2899c52c9e97e41f621863a9f3d26134bb0ff297b8087f58f8842629469d","observation_id":"bdba729a-104f-4b41-927f-4959ea9d23bb","resolution":{"observed_at":"2026-08-07T04:24:25.934863Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T04:24:25.740239Z","title":"Robust backdoor detection for deep learning via topological evolution dynamics,","venue":null,"work_id":"79ec3c6b-0db3-4d16-ae8d-49af4b7f739b","year":2024},"citing_paper":{"arxiv_id":"2506.10722","last_updated":"2025-06-12T14:12:15Z","snapshot_observed_at":"2026-08-07T04:17:18.839831Z","submitted_at":"2025-06-12T14:12:15Z","title":"TED-LaST: Towards Robust Backdoor Defense Against Adaptive Attacks","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T04:24:21.331832Z"},"links":{"citing_paper":"/paper/2506.10722"},"observation_digest":"sha256:b78dd67521f0d121c39c6bb067195299d0b9d37507a918bb19f331d0d303b7fd","observation_id":"695adf13-5f03-4792-8dcb-81820e7c40b2","resolution":{"observed_at":"2026-08-07T04:24:25.794515Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T04:24:25.605774Z","title":"Revisiting the assumption of latent separability for backdoor defenses,","venue":null,"work_id":"9f9a75fa-ad11-4b5c-acb2-bf89237dbb62","year":2022},"citing_paper":{"arxiv_id":"2506.10722","last_updated":"2025-06-12T14:12:15Z","snapshot_observed_at":"2026-08-07T04:17:18.839831Z","submitted_at":"2025-06-12T14:12:15Z","title":"TED-LaST: Towards Robust Backdoor Defense Against Adaptive Attacks","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T04:24:21.389580Z"},"links":{"citing_paper":"/paper/2506.10722"},"observation_digest":"sha256:8bee2a1060a82cde80997bcbb2e44a61ba5b3a01555a2277e4d93eb6a8ba0b7b","observation_id":"9f2e8f74-a879-4bb9-b94f-0a09ee5c87d1","resolution":{"observed_at":"2026-08-07T04:24:25.676036Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T04:24:25.451898Z","title":"Bypassing backdoor detection al- gorithms in deep learning,","venue":null,"work_id":"19249b12-cfff-4181-880b-3e28804498ea","year":2020},"citing_paper":{"arxiv_id":"2506.10722","last_updated":"2025-06-12T14:12:15Z","snapshot_observed_at":"2026-08-07T04:17:18.839831Z","submitted_at":"2025-06-12T14:12:15Z","title":"TED-LaST: Towards Robust Backdoor Defense Against Adaptive Attacks","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T04:24:21.459606Z"},"links":{"citing_paper":"/paper/2506.10722"},"observation_digest":"sha256:cb813914c2492e76f8e5eddba4a10f39f5be4418a11160afa79c296fe9d96965","observation_id":"b24005dd-0565-40a3-b9e4-7d57528186d4","resolution":{"observed_at":"2026-08-07T04:24:25.529402Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T04:24:25.297955Z","title":"Blind backdoors in deep learning models,","venue":null,"work_id":"4308781b-bf5b-4716-8649-2a631a28925c","year":2021},"citing_paper":{"arxiv_id":"2506.10722","last_updated":"2025-06-12T14:12:15Z","snapshot_observed_at":"2026-08-07T04:17:18.839831Z","submitted_at":"2025-06-12T14:12:15Z","title":"TED-LaST: Towards Robust Backdoor Defense Against Adaptive Attacks","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T04:24:21.504292Z"},"links":{"citing_paper":"/paper/2506.10722"},"observation_digest":"sha256:548a7ca817332359009a7a815a8e9c5fc9ad9588aa18d481ae9b6d5e2f72f9b4","observation_id":"e83d7a7b-3fd5-4a85-bdd1-5ae6f84dba5c","resolution":{"observed_at":"2026-08-07T04:24:25.380451Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T04:24:25.188943Z","title":"On model outsourcing adaptive attacks to deep learning backdoor defenses,","venue":null,"work_id":"07217e04-a24b-4d42-a49b-cc34a16f114d","year":2024},"citing_paper":{"arxiv_id":"2506.10722","last_updated":"2025-06-12T14:12:15Z","snapshot_observed_at":"2026-08-07T04:17:18.839831Z","submitted_at":"2025-06-12T14:12:15Z","title":"TED-LaST: Towards Robust Backdoor Defense Against Adaptive Attacks","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T04:24:21.575688Z"},"links":{"citing_paper":"/paper/2506.10722"},"observation_digest":"sha256:7cbe4dc4efd917dfc78823c77b91217ad5f7af3875ae3fbd527774e6c5a52c90","observation_id":"bbe1ac54-bf63-440c-845c-00a0623991ba","resolution":{"observed_at":"2026-08-07T04:24:25.252555Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T04:24:25.063790Z","title":"Dba: Distributed back- door attacks against federated learning,","venue":null,"work_id":"fdde0201-a3a3-459d-8a56-22b69e23facf","year":2020},"citing_paper":{"arxiv_id":"2506.10722","last_updated":"2025-06-12T14:12:15Z","snapshot_observed_at":"2026-08-07T04:17:18.839831Z","submitted_at":"2025-06-12T14:12:15Z","title":"TED-LaST: Towards Robust Backdoor Defense Against Adaptive Attacks","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T04:24:21.640497Z"},"links":{"citing_paper":"/paper/2506.10722"},"observation_digest":"sha256:33373e8553199c4716a7777ce408fb1567f3b19d7b455b1a1477eb008d71656f","observation_id":"f3be42f1-e104-4138-b83f-ea8594f70c90","resolution":{"observed_at":"2026-08-07T04:24:25.120653Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T04:24:24.955291Z","title":"One-to-n & n-to-one: Two advanced backdoor attacks against deep learning models,","venue":null,"work_id":"ae7399a6-0349-4ab5-a20c-354211ad327e","year":2020},"citing_paper":{"arxiv_id":"2506.10722","last_updated":"2025-06-12T14:12:15Z","snapshot_observed_at":"2026-08-07T04:17:18.839831Z","submitted_at":"2025-06-12T14:12:15Z","title":"TED-LaST: Towards Robust Backdoor Defense Against Adaptive Attacks","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T04:24:21.723719Z"},"links":{"citing_paper":"/paper/2506.10722"},"observation_digest":"sha256:49a6811557170aaad5ac2aa6a34425da02ece773701a8606f3cbf0c20ba2d7d9","observation_id":"fe92b652-c69e-4d52-95b4-d7e56f0173a1","resolution":{"observed_at":"2026-08-07T04:24:25.014857Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T04:24:24.815447Z","title":"A multitarget backdooring attack on deep neural networks with random location trigger,","venue":null,"work_id":"86131226-fc31-4656-aafa-2976515f298c","year":2022},"citing_paper":{"arxiv_id":"2506.10722","last_updated":"2025-06-12T14:12:15Z","snapshot_observed_at":"2026-08-07T04:17:18.839831Z","submitted_at":"2025-06-12T14:12:15Z","title":"TED-LaST: Towards Robust Backdoor Defense Against Adaptive Attacks","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T04:24:21.740860Z"},"links":{"citing_paper":"/paper/2506.10722"},"observation_digest":"sha256:9f1cfd0028bed59e9b48080ee4ecaf38d32d127c6ac42a126046cfdb716d1bf6","observation_id":"ed449bb3-80b1-4bda-a27e-ba97acf60baf","resolution":{"observed_at":"2026-08-07T04:24:24.862130Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T04:24:24.674184Z","title":"Spectre: Defending against backdoor attacks using robust statistics,","venue":null,"work_id":"8c0181cf-0d60-4c0f-8c39-5e6344c7b0a5","year":2021},"citing_paper":{"arxiv_id":"2506.10722","last_updated":"2025-06-12T14:12:15Z","snapshot_observed_at":"2026-08-07T04:17:18.839831Z","submitted_at":"2025-06-12T14:12:15Z","title":"TED-LaST: Towards Robust Backdoor Defense Against Adaptive Attacks","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T04:24:21.861922Z"},"links":{"citing_paper":"/paper/2506.10722"},"observation_digest":"sha256:daf3551d1182ca845dc65cb461aa9d6e8276942caf8c597a4a0b63681b79959b","observation_id":"ec7b16cc-8113-48e7-b084-ecaa9a0ed47f","resolution":{"observed_at":"2026-08-07T04:24:24.716676Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T04:24:24.523404Z","title":"Backdooring convolutional neural networks via targeted weight perturbations,","venue":null,"work_id":"bb7ff11e-4bf4-4047-b929-6db9260b0c9e","year":2020},"citing_paper":{"arxiv_id":"2506.10722","last_updated":"2025-06-12T14:12:15Z","snapshot_observed_at":"2026-08-07T04:17:18.839831Z","submitted_at":"2025-06-12T14:12:15Z","title":"TED-LaST: Towards Robust Backdoor Defense Against Adaptive Attacks","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T04:24:21.911154Z"},"links":{"citing_paper":"/paper/2506.10722"},"observation_digest":"sha256:8d95019c3c3b5a0a0e5938c15a2847a2a106b572ff0c79823b2f5b102df84688","observation_id":"5080476c-f6f4-41d8-a565-9b9465dd67b3","resolution":{"observed_at":"2026-08-07T04:24:24.580464Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T04:24:24.348567Z","title":"An embarrassingly simple approach for trojan attack in deep neural networks,","venue":null,"work_id":"ead59da7-5ef6-42a6-9d12-9a18fc581bc9","year":2020},"citing_paper":{"arxiv_id":"2506.10722","last_updated":"2025-06-12T14:12:15Z","snapshot_observed_at":"2026-08-07T04:17:18.839831Z","submitted_at":"2025-06-12T14:12:15Z","title":"TED-LaST: Towards Robust Backdoor Defense Against Adaptive Attacks","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T04:24:22.014191Z"},"links":{"citing_paper":"/paper/2506.10722"},"observation_digest":"sha256:172d296aae1a3ad1cd71e9a51585428cc0a65e0a6be8ac59b99c8b81d62bf1bf","observation_id":"52f18d5c-1e25-4b32-89a6-318308e1203a","resolution":{"observed_at":"2026-08-07T04:24:24.439176Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T04:24:24.122307Z","title":"Odyssey: Creation, analysis and detection of trojan models,","venue":null,"work_id":"721f685a-a90b-4774-adaf-f1a8f06a56d3","year":2021},"citing_paper":{"arxiv_id":"2506.10722","last_updated":"2025-06-12T14:12:15Z","snapshot_observed_at":"2026-08-07T04:17:18.839831Z","submitted_at":"2025-06-12T14:12:15Z","title":"TED-LaST: Towards Robust Backdoor Defense Against Adaptive Attacks","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T04:24:22.095972Z"},"links":{"citing_paper":"/paper/2506.10722"},"observation_digest":"sha256:3e5915f00c28658f06d8f6b0b5cecb7d63203c777508f233c49772c7973ac6d9","observation_id":"e9bdbacf-ac3f-4cf3-8f99-da7a5904ca6d","resolution":{"observed_at":"2026-08-07T04:24:24.227444Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T04:24:22.178809Z","title":"Detecting backdoor attacks on deep neural networks by activation clustering,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.10722","last_updated":"2025-06-12T14:12:15Z","snapshot_observed_at":"2026-08-07T04:17:18.839831Z","submitted_at":"2025-06-12T14:12:15Z","title":"TED-LaST: Towards Robust Backdoor Defense Against Adaptive Attacks","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T04:24:22.178809Z"},"links":{"cited_paper":"/paper/1811.03728","citing_paper":"/paper/2506.10722"},"observation_digest":"sha256:d7f1f43a5baa3aff578ff40e54548df9690b2c97bb7d87fd9d2458452a357c14","observation_id":"9ab03294-8c14-4815-b7e9-207690d6b300","resolution":{"observed_at":"2026-08-07T04:24:22.178809Z","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":"2026-08-07T04:24:23.943170Z","title":"Backdoor defense via decoupling the training process,","venue":null,"work_id":"d450c059-1b9a-4363-94ed-c9cda0072f04","year":2022},"citing_paper":{"arxiv_id":"2506.10722","last_updated":"2025-06-12T14:12:15Z","snapshot_observed_at":"2026-08-07T04:17:18.839831Z","submitted_at":"2025-06-12T14:12:15Z","title":"TED-LaST: Towards Robust Backdoor Defense Against Adaptive Attacks","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-07T04:24:22.237459Z"},"links":{"citing_paper":"/paper/2506.10722"},"observation_digest":"sha256:6cf9352c92d6c810964133cb7886628a79e086caba32eaa0293ed551495f462e","observation_id":"96b9fb7c-5b06-49de-b746-c6c47ab7bd8d","resolution":{"observed_at":"2026-08-07T04:24:24.027592Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T04:24:23.711337Z","title":"Defending against backdoor attacks by layer-wise feature analysis,","venue":null,"work_id":"4d2d984c-7b13-4db9-938e-1d4204bf98a8","year":2023},"citing_paper":{"arxiv_id":"2506.10722","last_updated":"2025-06-12T14:12:15Z","snapshot_observed_at":"2026-08-07T04:17:18.839831Z","submitted_at":"2025-06-12T14:12:15Z","title":"TED-LaST: Towards Robust Backdoor Defense Against Adaptive Attacks","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-07T04:24:22.326724Z"},"links":{"citing_paper":"/paper/2506.10722"},"observation_digest":"sha256:67b013a975fbd41e6c744fd88636624aaffdc184cf6cbf98cb35ec137d8dd5e4","observation_id":"a2b26ebd-50cc-45d4-acc2-e77a45af8388","resolution":{"observed_at":"2026-08-07T04:24:23.810097Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T04:24:22.374798Z","title":"Modularity and community structure in networks,","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2506.10722","last_updated":"2025-06-12T14:12:15Z","snapshot_observed_at":"2026-08-07T04:17:18.839831Z","submitted_at":"2025-06-12T14:12:15Z","title":"TED-LaST: Towards Robust Backdoor Defense Against Adaptive Attacks","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T04:24:22.374798Z"},"links":{"citing_paper":"/paper/2506.10722"},"observation_digest":"sha256:e39453649465cbd9d4fd8f1aace16815c7ffe7da39af0d20695504e97529ae4c","observation_id":"434e833e-c9ae-4cdc-88e3-f330493f2b2e","resolution":{"observed_at":"2026-08-07T04:24:22.374798Z","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":"2026-08-07T04:24:22.483050Z","title":"Community detection in graphs,","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2506.10722","last_updated":"2025-06-12T14:12:15Z","snapshot_observed_at":"2026-08-07T04:17:18.839831Z","submitted_at":"2025-06-12T14:12:15Z","title":"TED-LaST: Towards Robust Backdoor Defense Against Adaptive Attacks","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-07T04:24:22.483050Z"},"links":{"citing_paper":"/paper/2506.10722"},"observation_digest":"sha256:c3d6bb07be8947b299d91a591546d62b9dea6424a3978d56f60bc3a36e1b2b66","observation_id":"8e630290-24f4-4138-812f-302aa243ca3d","resolution":{"observed_at":"2026-08-07T04:24:22.483050Z","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":"2026-08-07T04:24:22.520337Z","title":"Pyod: A python toolbox for scalable outlier detection,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.10722","last_updated":"2025-06-12T14:12:15Z","snapshot_observed_at":"2026-08-07T04:17:18.839831Z","submitted_at":"2025-06-12T14:12:15Z","title":"TED-LaST: Towards Robust Backdoor Defense Against Adaptive Attacks","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-07T04:24:22.520337Z"},"links":{"citing_paper":"/paper/2506.10722"},"observation_digest":"sha256:7e6ef5d668c328fc5c6c3d0a26bc9f5c59aa54096a1ca590ca75707db70bb7d0","observation_id":"a8486ee6-077b-4031-847d-c58a9b903a63","resolution":{"observed_at":"2026-08-07T04:24:22.520337Z","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":"2026-08-07T04:24:23.487278Z","title":"The cifar-10 dataset,","venue":null,"work_id":"b5b0be08-33b6-44f5-81e6-675d7d8c9b5a","year":null},"citing_paper":{"arxiv_id":"2506.10722","last_updated":"2025-06-12T14:12:15Z","snapshot_observed_at":"2026-08-07T04:17:18.839831Z","submitted_at":"2025-06-12T14:12:15Z","title":"TED-LaST: Towards Robust Backdoor Defense Against Adaptive Attacks","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-07T04:24:22.613298Z"},"links":{"citing_paper":"/paper/2506.10722"},"observation_digest":"sha256:80a46f98e253460545b48e9ffe1a7cbc8e268788f620b6536f2e5c47612c9912","observation_id":"d28b8ab2-c1d5-4fcb-89a6-c676cef23b94","resolution":{"observed_at":"2026-08-07T04:24:23.592352Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T04:24:23.282915Z","title":"Man vs. computer: Benchmarking machine learning algorithms for traffic sign recognition,","venue":null,"work_id":"c8619639-9df2-4621-9b68-9e4ea2247c66","year":2012},"citing_paper":{"arxiv_id":"2506.10722","last_updated":"2025-06-12T14:12:15Z","snapshot_observed_at":"2026-08-07T04:17:18.839831Z","submitted_at":"2025-06-12T14:12:15Z","title":"TED-LaST: Towards Robust Backdoor Defense Against Adaptive Attacks","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-07T04:24:22.710585Z"},"links":{"citing_paper":"/paper/2506.10722"},"observation_digest":"sha256:983ef887a3d2066bf1652012651c17e8832ea53715ea27a67fde9887be3a2391","observation_id":"1577b5ae-bdc1-44c9-bc8b-afa41f870f22","resolution":{"observed_at":"2026-08-07T04:24:23.381078Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T04:24:22.841169Z","title":"Deep residual learning for image recognition,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2506.10722","last_updated":"2025-06-12T14:12:15Z","snapshot_observed_at":"2026-08-07T04:17:18.839831Z","submitted_at":"2025-06-12T14:12:15Z","title":"TED-LaST: Towards Robust Backdoor Defense Against Adaptive Attacks","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-07T04:24:22.841169Z"},"links":{"citing_paper":"/paper/2506.10722"},"observation_digest":"sha256:9a5da21771e24bf1ee2e2362518cad3ddd916ef165f331a573f9cfab59dbf70e","observation_id":"1b63b13f-f4a8-4c53-9a03-a62ec5935639","resolution":{"observed_at":"2026-08-07T04:24:22.841169Z","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":"2026-08-07T04:24:23.145147Z","title":"Imagenet: A large-scale hierarchical image database,","venue":null,"work_id":"e99d1260-21d5-4854-93e2-e800f53b2f8d","year":2009},"citing_paper":{"arxiv_id":"2506.10722","last_updated":"2025-06-12T14:12:15Z","snapshot_observed_at":"2026-08-07T04:17:18.839831Z","submitted_at":"2025-06-12T14:12:15Z","title":"TED-LaST: Towards Robust Backdoor Defense Against Adaptive Attacks","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-07T04:24:22.959017Z"},"links":{"citing_paper":"/paper/2506.10722"},"observation_digest":"sha256:b580947555db1d743a47b8d8fff528473eac946975830e1e9bf3f9bc38309f2e","observation_id":"21e3bbca-7535-4e3c-9233-4d39517f86a3","resolution":{"observed_at":"2026-08-07T04:24:23.228441Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2506.10722","last_updated":"2025-06-12T14:12:15Z","latest_version":1,"primary_category":"cs.CR","snapshot_observed_at":"2026-08-07T04:17:18.839831Z","submitted_at":"2025-06-12T14:12:15Z","title":"TED-LaST: Towards Robust Backdoor Defense Against Adaptive Attacks"},"reference_resolution":{"displayed":49,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":8,"verified_exact":0,"verified_fuzzy":41},"total_outbound_references":49},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 49 of 49 outbound references and 0 inbound Pith citation observations for arXiv:2506.10722."}