{"as_of":"2026-08-13T00:45:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d9734ac0a10552ebc16f99f1390d63f35a1de12de9e1a17db5673b2aa26a6f47","coverage":[{"denominator":44,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":44,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T22:05:21.658856Z","state":"measured"},{"denominator":44,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":44,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-12T06:34:41.77262+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2412.03908/citation-record","integrity":"/paper/2412.03908/integrity","json":"/paper/2412.03908/citation-record.json","paper":"/paper/2412.03908"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:05:22.309729Z","title":"Bullseye polytope: A scalable clean-label poisoning attack with improved trans- ferability","venue":null,"work_id":"0e869779-9138-492b-8d5c-91b504e60535","year":2021},"citing_paper":{"arxiv_id":"2412.03908","last_updated":"2025-07-26T03:30:55Z","snapshot_observed_at":"2026-08-11T21:55:21.186265Z","submitted_at":"2024-12-05T06:27:14Z","title":"Generalizable Targeted Data Poisoning against Varying Physical Objects","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-11T22:05:21.455106Z"},"links":{"citing_paper":"/paper/2412.03908"},"observation_digest":"sha256:9f53f49ac6d6dfbfc235bf51c9a9b6b89ead8f5a1f63eca79139062621e92bca","observation_id":"c519394a-3418-4a31-a4db-0b1996cc0a0d","resolution":{"observed_at":"2026-08-11T22:05:22.314262Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:05:22.295818Z","title":"Poison- ing attacks against support vector machines","venue":null,"work_id":"7c394bb2-09f7-44ce-beb7-4ec5b178e0dd","year":2012},"citing_paper":{"arxiv_id":"2412.03908","last_updated":"2025-07-26T03:30:55Z","snapshot_observed_at":"2026-08-11T21:55:21.186265Z","submitted_at":"2024-12-05T06:27:14Z","title":"Generalizable Targeted Data Poisoning against Varying Physical Objects","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-11T22:05:21.460177Z"},"links":{"citing_paper":"/paper/2412.03908"},"observation_digest":"sha256:c08371ba86f8385bf5bf1555cf765d8b51d1a578456e2a69763206eda6b5e973","observation_id":"49287561-92a6-4a8c-a477-9ae4f4245a66","resolution":{"observed_at":"2026-08-11T22:05:22.300205Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:05:22.280879Z","title":"Poisoning web-scale training datasets is practical","venue":null,"work_id":"f74adf58-045a-4505-835d-31d3b8517e2f","year":null},"citing_paper":{"arxiv_id":"2412.03908","last_updated":"2025-07-26T03:30:55Z","snapshot_observed_at":"2026-08-11T21:55:21.186265Z","submitted_at":"2024-12-05T06:27:14Z","title":"Generalizable Targeted Data Poisoning against Varying Physical Objects","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-11T22:05:21.464779Z"},"links":{"citing_paper":"/paper/2412.03908"},"observation_digest":"sha256:4083bf7cdc73521ca50e215a17db8f28994a91b1d67946e2131904453981038b","observation_id":"b4c439b5-ef58-48e6-94b9-b125c3584217","resolution":{"observed_at":"2026-08-11T22:05:22.285976Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:05:21.469298Z","title":"Conceptual 12m: Pushing web-scale image-text pre- training to recognize long-tail visual concepts","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.03908","last_updated":"2025-07-26T03:30:55Z","snapshot_observed_at":"2026-08-11T21:55:21.186265Z","submitted_at":"2024-12-05T06:27:14Z","title":"Generalizable Targeted Data Poisoning against Varying Physical Objects","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-11T22:05:21.469298Z"},"links":{"citing_paper":"/paper/2412.03908"},"observation_digest":"sha256:8caf5acff182e8bbee9a9ee87af5ecb230a903c844f465a3fb01caac027c4d55","observation_id":"e8e427ff-a337-4a0c-8171-a80ad7676c25","resolution":{"observed_at":"2026-08-11T22:05:21.469298Z","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":"2026-08-11T22:05:22.254988Z","title":"Wild patterns reloaded: A survey of machine learning security against training data poisoning","venue":null,"work_id":"b40148e4-65b7-4b1c-8453-891f13b5a079","year":2023},"citing_paper":{"arxiv_id":"2412.03908","last_updated":"2025-07-26T03:30:55Z","snapshot_observed_at":"2026-08-11T21:55:21.186265Z","submitted_at":"2024-12-05T06:27:14Z","title":"Generalizable Targeted Data Poisoning against Varying Physical Objects","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-11T22:05:21.473878Z"},"links":{"citing_paper":"/paper/2412.03908"},"observation_digest":"sha256:76dba5e6b06e7d8afb4682983a11ba45d22a28a7515babdfd3d3ea28f90f80cb","observation_id":"31452b6b-ad77-48f3-8f19-00d8f01266ea","resolution":{"observed_at":"2026-08-11T22:05:22.259912Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:05:22.239865Z","title":"Robust unlearnable examples: Protecting data privacy against adversarial learning","venue":null,"work_id":"6cd0cc08-edc0-4784-86d4-bdfa682c9587","year":2022},"citing_paper":{"arxiv_id":"2412.03908","last_updated":"2025-07-26T03:30:55Z","snapshot_observed_at":"2026-08-11T21:55:21.186265Z","submitted_at":"2024-12-05T06:27:14Z","title":"Generalizable Targeted Data Poisoning against Varying Physical Objects","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-11T22:05:21.478800Z"},"links":{"citing_paper":"/paper/2412.03908"},"observation_digest":"sha256:5376dfc2dcb1642481c22c81df9d46f78f10250d7d84efc93dbc7eee612f8b44","observation_id":"bb94a5d1-1796-4a0a-88bf-ec6404784a58","resolution":{"observed_at":"2026-08-11T22:05:22.244714Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:05:22.224948Z","title":"Dat- acomp: In search of the next generation of multimodal datasets","venue":null,"work_id":"a2bf5af2-49c2-46ac-91ff-34c2989b6675","year":2024},"citing_paper":{"arxiv_id":"2412.03908","last_updated":"2025-07-26T03:30:55Z","snapshot_observed_at":"2026-08-11T21:55:21.186265Z","submitted_at":"2024-12-05T06:27:14Z","title":"Generalizable Targeted Data Poisoning against Varying Physical Objects","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-11T22:05:21.483586Z"},"links":{"citing_paper":"/paper/2412.03908"},"observation_digest":"sha256:3b86fd1f13f4002714acf8933b5265195ea29d4b65ab442bd6c1a3419efe9f88","observation_id":"35bf5daa-312b-43c9-851a-a2cb2fd34fcb","resolution":{"observed_at":"2026-08-11T22:05:22.229926Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:05:22.210144Z","title":"Ronny Huang, Wojciech Czaja, Gavin Taylor, Michael Moeller, and Tom Goldstein","venue":null,"work_id":"f9a61618-d217-42d3-84dd-bf4e74ffa145","year":2021},"citing_paper":{"arxiv_id":"2412.03908","last_updated":"2025-07-26T03:30:55Z","snapshot_observed_at":"2026-08-11T21:55:21.186265Z","submitted_at":"2024-12-05T06:27:14Z","title":"Generalizable Targeted Data Poisoning against Varying Physical Objects","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-11T22:05:21.489224Z"},"links":{"citing_paper":"/paper/2412.03908"},"observation_digest":"sha256:7bb785f36fa23ab8687bc2517f08357cdef6edb6f005080a3325b3f667a379d5","observation_id":"a59f8fa6-527e-4e68-9a0a-c61772bf2f8a","resolution":{"observed_at":"2026-08-11T22:05:22.215051Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:05:22.195191Z","title":"Dataset security for machine learning: Data poisoning, backdoor attacks, and defenses","venue":null,"work_id":"215a4726-383d-4dba-96fb-1b8e357c5090","year":2023},"citing_paper":{"arxiv_id":"2412.03908","last_updated":"2025-07-26T03:30:55Z","snapshot_observed_at":"2026-08-11T21:55:21.186265Z","submitted_at":"2024-12-05T06:27:14Z","title":"Generalizable Targeted Data Poisoning against Varying Physical Objects","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-11T22:05:21.494301Z"},"links":{"citing_paper":"/paper/2412.03908"},"observation_digest":"sha256:9deab756065db45efd8c37a11bfb997b9ee0c5f3b59ca29791c702dc8bb12e08","observation_id":"e717f727-9ba5-43bc-9c29-79c005d9693f","resolution":{"observed_at":"2026-08-11T22:05:22.200061Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:05:21.498973Z","title":"Levit: a vision transformer in convnet’s clothing for faster inference","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.03908","last_updated":"2025-07-26T03:30:55Z","snapshot_observed_at":"2026-08-11T21:55:21.186265Z","submitted_at":"2024-12-05T06:27:14Z","title":"Generalizable Targeted Data Poisoning against Varying Physical Objects","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-11T22:05:21.498973Z"},"links":{"citing_paper":"/paper/2412.03908"},"observation_digest":"sha256:3588961f5b53cc51108631b306aed50bc299adf033092bf6bf98c746aa0b1d01","observation_id":"49af4650-4b74-405e-89d8-e6765e267d41","resolution":{"observed_at":"2026-08-11T22:05:21.498973Z","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":"2026-08-11T22:05:22.170576Z","title":"Badnets: Evaluating backdooring attacks on deep neu- ral networks","venue":null,"work_id":"f7af4d72-93aa-419a-bcf5-09dabd0f0247","year":2019},"citing_paper":{"arxiv_id":"2412.03908","last_updated":"2025-07-26T03:30:55Z","snapshot_observed_at":"2026-08-11T21:55:21.186265Z","submitted_at":"2024-12-05T06:27:14Z","title":"Generalizable Targeted Data Poisoning against Varying Physical Objects","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-11T22:05:21.503813Z"},"links":{"citing_paper":"/paper/2412.03908"},"observation_digest":"sha256:67fb7d2632d6e14123907e0b0308d128e35447b099a1f190beff6541ffe6ae95","observation_id":"b8341511-dc48-410c-aa03-146cb2aa17c2","resolution":{"observed_at":"2026-08-11T22:05:22.175380Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2002.11497","last_updated":"2020-02-27T19:00:01Z","snapshot_observed_at":"2026-08-05T18:32:59.157848Z","submitted_at":"2020-02-26T14:04:16Z","title":"On the Effectiveness of Mitigating Data Poisoning Attacks with Gradient Shaping","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.11497","snapshot_observed_at":"2026-08-11T22:05:21.508776Z","title":"On the effectiveness of mitigating data poisoning attacks with gradient shaping","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2412.03908","last_updated":"2025-07-26T03:30:55Z","snapshot_observed_at":"2026-08-11T21:55:21.186265Z","submitted_at":"2024-12-05T06:27:14Z","title":"Generalizable Targeted Data Poisoning against Varying Physical Objects","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-11T22:05:21.508776Z"},"links":{"cited_paper":"/paper/2002.11497","citing_paper":"/paper/2412.03908"},"observation_digest":"sha256:ef11c73d07f1513ec7c4718805346c38ff2775f525395b233e8faa1a5b34a5da","observation_id":"21ae2857-357f-4fe7-832e-00efd6e05a87","resolution":{"observed_at":"2026-08-11T22:05:21.508776Z","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":"2026-08-11T22:05:22.155764Z","title":"Nat- uralistic physical adversarial patch for object detectors","venue":null,"work_id":"840af21f-6e15-4d4c-878c-56257826b48b","year":2021},"citing_paper":{"arxiv_id":"2412.03908","last_updated":"2025-07-26T03:30:55Z","snapshot_observed_at":"2026-08-11T21:55:21.186265Z","submitted_at":"2024-12-05T06:27:14Z","title":"Generalizable Targeted Data Poisoning against Varying Physical Objects","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-11T22:05:21.513729Z"},"links":{"citing_paper":"/paper/2412.03908"},"observation_digest":"sha256:bd3acb21ac8b858c712d1fbeb4437db464d23b303d31eef2ff0dfe3548fc3901","observation_id":"9ddba6bb-ddba-4181-95cd-02f4812196ba","resolution":{"observed_at":"2026-08-11T22:05:22.160491Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:05:21.518338Z","title":"Adversarial texture for fooling person detectors in the physical world","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.03908","last_updated":"2025-07-26T03:30:55Z","snapshot_observed_at":"2026-08-11T21:55:21.186265Z","submitted_at":"2024-12-05T06:27:14Z","title":"Generalizable Targeted Data Poisoning against Varying Physical Objects","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-11T22:05:21.518338Z"},"links":{"citing_paper":"/paper/2412.03908"},"observation_digest":"sha256:01aab9920d7b3eca90fce3b9e78aacbd19faa771c1c823f6187e7970c630b9c9","observation_id":"547fb8e1-ee2f-4c22-ad35-71ac8f580434","resolution":{"observed_at":"2026-08-11T22:05:21.518338Z","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":"2026-08-11T22:05:22.131205Z","title":"Unlearnable examples: Making personal data unexploitable","venue":null,"work_id":"49bfd9d1-54d9-43a5-a24d-620f15d95c8b","year":2021},"citing_paper":{"arxiv_id":"2412.03908","last_updated":"2025-07-26T03:30:55Z","snapshot_observed_at":"2026-08-11T21:55:21.186265Z","submitted_at":"2024-12-05T06:27:14Z","title":"Generalizable Targeted Data Poisoning against Varying Physical Objects","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-11T22:05:21.523069Z"},"links":{"citing_paper":"/paper/2412.03908"},"observation_digest":"sha256:b84d6c3eb5d6dff49eab818a172fbde85f916c0e55f1e6020dc4f24f0d32af89","observation_id":"f8e36101-abc8-4e51-a989-4a670f62ff1c","resolution":{"observed_at":"2026-08-11T22:05:22.135960Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:05:22.116065Z","title":"T-sea: Transfer-based self-ensemble attack on object detection","venue":null,"work_id":"e292f86c-9ee9-4612-8afc-12a572014a3b","year":2023},"citing_paper":{"arxiv_id":"2412.03908","last_updated":"2025-07-26T03:30:55Z","snapshot_observed_at":"2026-08-11T21:55:21.186265Z","submitted_at":"2024-12-05T06:27:14Z","title":"Generalizable Targeted Data Poisoning against Varying Physical Objects","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-11T22:05:21.527280Z"},"links":{"citing_paper":"/paper/2412.03908"},"observation_digest":"sha256:e6318fde83754d2ec6ec8f772177ae147b51a8ab67f13247bc800caf6b3be59e","observation_id":"0bf3c6ee-8af0-477a-adfc-183241101d42","resolution":{"observed_at":"2026-08-11T22:05:22.121158Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:05:22.101475Z","title":"Ronny Huang, Jonas Geiping, Liam Fowl, Gavin Taylor, and Tom Goldstein","venue":null,"work_id":"e9dd7723-f32d-4b60-8cd8-8a14bbb295f3","year":2020},"citing_paper":{"arxiv_id":"2412.03908","last_updated":"2025-07-26T03:30:55Z","snapshot_observed_at":"2026-08-11T21:55:21.186265Z","submitted_at":"2024-12-05T06:27:14Z","title":"Generalizable Targeted Data Poisoning against Varying Physical Objects","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-11T22:05:21.531466Z"},"links":{"citing_paper":"/paper/2412.03908"},"observation_digest":"sha256:5d43bf83df2781898427c34aee4aa45f129a8871d7463eb3987ca9d82bdaee29","observation_id":"1b48dd63-c3aa-4cc5-9727-eaf10c575370","resolution":{"observed_at":"2026-08-11T22:05:22.106095Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:05:22.087036Z","title":"Subpopulation data poisoning attacks","venue":null,"work_id":"e46bc270-8f19-48fb-848a-c6b9e97172a3","year":2021},"citing_paper":{"arxiv_id":"2412.03908","last_updated":"2025-07-26T03:30:55Z","snapshot_observed_at":"2026-08-11T21:55:21.186265Z","submitted_at":"2024-12-05T06:27:14Z","title":"Generalizable Targeted Data Poisoning against Varying Physical Objects","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-11T22:05:21.535569Z"},"links":{"citing_paper":"/paper/2412.03908"},"observation_digest":"sha256:cfc55fcf50b1cbd9e3d22641a431f7ce696fbdd166a86304c4d4a70e432fae4b","observation_id":"c6f98813-cd59-427c-aebf-f347e5b9edae","resolution":{"observed_at":"2026-08-11T22:05:22.091200Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:05:21.539328Z","title":"Lavan: Localized and visible adversarial noise","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.03908","last_updated":"2025-07-26T03:30:55Z","snapshot_observed_at":"2026-08-11T21:55:21.186265Z","submitted_at":"2024-12-05T06:27:14Z","title":"Generalizable Targeted Data Poisoning against Varying Physical Objects","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-11T22:05:21.539328Z"},"links":{"citing_paper":"/paper/2412.03908"},"observation_digest":"sha256:31e68047bfa063d715585c1acd0bec78eddea8f61ac335313ad4ee5bb1beacb2","observation_id":"e43a5f37-05c0-4644-9b91-369984dc64c7","resolution":{"observed_at":"2026-08-11T22:05:21.539328Z","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":"2026-08-11T22:05:22.062675Z","title":"Understanding black-box predictions via influence functions","venue":null,"work_id":"dfa08082-aa9d-4e74-820b-cb0a75a04258","year":2017},"citing_paper":{"arxiv_id":"2412.03908","last_updated":"2025-07-26T03:30:55Z","snapshot_observed_at":"2026-08-11T21:55:21.186265Z","submitted_at":"2024-12-05T06:27:14Z","title":"Generalizable Targeted Data Poisoning against Varying Physical Objects","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-11T22:05:21.545211Z"},"links":{"citing_paper":"/paper/2412.03908"},"observation_digest":"sha256:3e940316cc47105e51dd389930d157a0106a5d3566708203876ba07537c31577","observation_id":"9b555125-0be3-4d16-8298-4e6c1117dcbb","resolution":{"observed_at":"2026-08-11T22:05:22.067671Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.08076","last_updated":"2023-07-16T15:22:30Z","snapshot_observed_at":"2026-08-06T17:14:47.366139Z","submitted_at":"2023-07-16T15:22:30Z","title":"Diffusion to Confusion: Naturalistic Adversarial Patch Generation Based on Diffusion Model for Object Detector","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.08076","snapshot_observed_at":"2026-08-11T22:05:21.549858Z","title":"Diffusion to confusion: Naturalistic adversarial patch generation based on diffusion model for object detector","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.03908","last_updated":"2025-07-26T03:30:55Z","snapshot_observed_at":"2026-08-11T21:55:21.186265Z","submitted_at":"2024-12-05T06:27:14Z","title":"Generalizable Targeted Data Poisoning against Varying Physical Objects","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-11T22:05:21.549858Z"},"links":{"cited_paper":"/paper/2307.08076","citing_paper":"/paper/2412.03908"},"observation_digest":"sha256:d34e1f33b359a7ddcd3fed94426be153b6f4fe26c000ba3dc6615507a091cb52","observation_id":"37286e12-3ab3-466f-97a7-e4ddae664746","resolution":{"observed_at":"2026-08-11T22:05:21.549858Z","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":"2026-08-11T22:05:22.048301Z","title":"Swin transformer v2: Scaling up capacity and resolution","venue":null,"work_id":"8de0925a-ebcc-452d-9d33-6c13604c34ae","year":2022},"citing_paper":{"arxiv_id":"2412.03908","last_updated":"2025-07-26T03:30:55Z","snapshot_observed_at":"2026-08-11T21:55:21.186265Z","submitted_at":"2024-12-05T06:27:14Z","title":"Generalizable Targeted Data Poisoning against Varying Physical Objects","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-11T22:05:21.554950Z"},"links":{"citing_paper":"/paper/2412.03908"},"observation_digest":"sha256:176db1c6fadc4a1e854712ad140ca43445dd7942a9aed7f49d8c9f31e37a6bcb","observation_id":"432aa5f2-f2f3-4e4c-bc4e-be6d4c8f0c03","resolution":{"observed_at":"2026-08-11T22:05:22.052531Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:05:22.034146Z","title":"Image shortcut squeezing: Countering perturbative availability poi- sons with compression","venue":null,"work_id":"e7411d44-65fa-4a34-8abc-ece858e80943","year":2023},"citing_paper":{"arxiv_id":"2412.03908","last_updated":"2025-07-26T03:30:55Z","snapshot_observed_at":"2026-08-11T21:55:21.186265Z","submitted_at":"2024-12-05T06:27:14Z","title":"Generalizable Targeted Data Poisoning against Varying Physical Objects","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-11T22:05:21.559860Z"},"links":{"citing_paper":"/paper/2412.03908"},"observation_digest":"sha256:a145d00f3e41fb9c1b199ee6480629671b618697fe7a8ddf3ad751837524a152","observation_id":"bf7def1c-da81-494c-993b-f8665d3c7c5b","resolution":{"observed_at":"2026-08-11T22:05:22.038768Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:05:22.019359Z","title":"Towards poisoning of deep learning algorithms with back-gradient optimization","venue":null,"work_id":"5753517a-7bf7-4334-8513-28e8cb818aac","year":2017},"citing_paper":{"arxiv_id":"2412.03908","last_updated":"2025-07-26T03:30:55Z","snapshot_observed_at":"2026-08-11T21:55:21.186265Z","submitted_at":"2024-12-05T06:27:14Z","title":"Generalizable Targeted Data Poisoning against Varying Physical Objects","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-11T22:05:21.565053Z"},"links":{"citing_paper":"/paper/2412.03908"},"observation_digest":"sha256:976a32c6627c21626283603602e719500593cbc178651b9c289127fdd4c9717f","observation_id":"ab2a9a29-faa6-4764-ad7a-a150b9cfd871","resolution":{"observed_at":"2026-08-11T22:05:22.024280Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:05:22.003549Z","title":"Pose es- timation for category specific multiview object localization","venue":null,"work_id":"387df11b-21e6-4993-980d-3411de60daa7","year":2009},"citing_paper":{"arxiv_id":"2412.03908","last_updated":"2025-07-26T03:30:55Z","snapshot_observed_at":"2026-08-11T21:55:21.186265Z","submitted_at":"2024-12-05T06:27:14Z","title":"Generalizable Targeted Data Poisoning against Varying Physical Objects","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-11T22:05:21.569663Z"},"links":{"citing_paper":"/paper/2412.03908"},"observation_digest":"sha256:999770eb81737c8f10d86ad4c41d4ef70ea9e07c1bfe6964d34d424520906cc2","observation_id":"c1696f21-0e41-49ae-bfcc-b5ed4b4aa41d","resolution":{"observed_at":"2026-08-11T22:05:22.009403Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:05:21.988852Z","title":"Hidden trigger backdoor attacks, 2019","venue":null,"work_id":"14ba25f5-dd56-4fea-8963-7b6477c6df08","year":2019},"citing_paper":{"arxiv_id":"2412.03908","last_updated":"2025-07-26T03:30:55Z","snapshot_observed_at":"2026-08-11T21:55:21.186265Z","submitted_at":"2024-12-05T06:27:14Z","title":"Generalizable Targeted Data Poisoning against Varying Physical Objects","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-11T22:05:21.574281Z"},"links":{"citing_paper":"/paper/2412.03908"},"observation_digest":"sha256:5d463d141eeaa2eca3899818db41867aaac3568be1dc2b2d58afc41594298c20","observation_id":"d5e26fc7-0601-490a-b46d-939bd6b5a77a","resolution":{"observed_at":"2026-08-11T22:05:21.993653Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:05:21.578964Z","title":"Laion-5b: An open large-scale dataset for training next generation image-text models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.03908","last_updated":"2025-07-26T03:30:55Z","snapshot_observed_at":"2026-08-11T21:55:21.186265Z","submitted_at":"2024-12-05T06:27:14Z","title":"Generalizable Targeted Data Poisoning against Varying Physical Objects","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-11T22:05:21.578964Z"},"links":{"citing_paper":"/paper/2412.03908"},"observation_digest":"sha256:57d9fb2a49869c73f03d2af1003d46150fd83b7e3d6dc9ad8999e5f8f15517db","observation_id":"137585fa-d8b1-4fac-bd83-8d8c79923df3","resolution":{"observed_at":"2026-08-11T22:05:21.578964Z","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":"2026-08-11T22:05:21.962776Z","title":"Just how toxic is data poison- ing? a unified benchmark for backdoor and data poisoning attacks","venue":null,"work_id":"51c47f47-b6aa-4251-a587-7bad1053d129","year":2021},"citing_paper":{"arxiv_id":"2412.03908","last_updated":"2025-07-26T03:30:55Z","snapshot_observed_at":"2026-08-11T21:55:21.186265Z","submitted_at":"2024-12-05T06:27:14Z","title":"Generalizable Targeted Data Poisoning against Varying Physical Objects","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-11T22:05:21.585325Z"},"links":{"citing_paper":"/paper/2412.03908"},"observation_digest":"sha256:044e9ca6abfc55f69d548be63ca8a53c04de0306af2b837a9ebf2824ea8e7111","observation_id":"48e95b7d-e6d3-4f96-b887-1c4d78cce99e","resolution":{"observed_at":"2026-08-11T22:05:21.967602Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:05:21.947987Z","title":"Poison frogs! targeted clean-label poisoning attacks on neu- ral networks","venue":null,"work_id":"758851e5-b167-4ff8-9707-cf72ad20b788","year":2018},"citing_paper":{"arxiv_id":"2412.03908","last_updated":"2025-07-26T03:30:55Z","snapshot_observed_at":"2026-08-11T21:55:21.186265Z","submitted_at":"2024-12-05T06:27:14Z","title":"Generalizable Targeted Data Poisoning against Varying Physical Objects","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-11T22:05:21.589961Z"},"links":{"citing_paper":"/paper/2412.03908"},"observation_digest":"sha256:3b173328ac43c0fb5b4b73e17c031079ee1b6ed14d38ee6e5aca70a4b5900d1f","observation_id":"8fb461d7-2c8e-4d79-b72b-f8a09ae4fc9d","resolution":{"observed_at":"2026-08-11T22:05:21.952786Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:05:21.932719Z","title":"Conceptual captions: A cleaned, hypernymed, im- age alt-text dataset for automatic image captioning","venue":null,"work_id":"5bd994ef-136a-4d18-bb58-dc265dd83c5c","year":2018},"citing_paper":{"arxiv_id":"2412.03908","last_updated":"2025-07-26T03:30:55Z","snapshot_observed_at":"2026-08-11T21:55:21.186265Z","submitted_at":"2024-12-05T06:27:14Z","title":"Generalizable Targeted Data Poisoning against Varying Physical Objects","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-11T22:05:21.594473Z"},"links":{"citing_paper":"/paper/2412.03908"},"observation_digest":"sha256:31e447c26ea328050d99c8c11c8ea90da53f52263b1c6734e85c07c98313aede","observation_id":"d526eac1-6e7a-44dc-ae5e-019e1691efbc","resolution":{"observed_at":"2026-08-11T22:05:21.937995Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:05:21.917817Z","title":"Sleeper agent: Scalable hidden trigger backdoors for neural networks trained from scratch","venue":null,"work_id":"259c207c-2007-4a2e-9b43-b1145cb54cf5","year":2022},"citing_paper":{"arxiv_id":"2412.03908","last_updated":"2025-07-26T03:30:55Z","snapshot_observed_at":"2026-08-11T21:55:21.186265Z","submitted_at":"2024-12-05T06:27:14Z","title":"Generalizable Targeted Data Poisoning against Varying Physical Objects","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-11T22:05:21.599192Z"},"links":{"citing_paper":"/paper/2412.03908"},"observation_digest":"sha256:7bdd1f063a11cf7379a963242309bc3869ef70f90b01c64fe259131b0a3814f6","observation_id":"370f5d68-49f2-4bf6-b459-36eb35b4a20e","resolution":{"observed_at":"2026-08-11T22:05:21.922915Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:05:21.901995Z","title":"Cer- tified defenses for data poisoning attacks.Advances in neural information processing systems, 30, 2017","venue":null,"work_id":"7ac98e0a-56be-405e-8abb-3f3d95484dce","year":2017},"citing_paper":{"arxiv_id":"2412.03908","last_updated":"2025-07-26T03:30:55Z","snapshot_observed_at":"2026-08-11T21:55:21.186265Z","submitted_at":"2024-12-05T06:27:14Z","title":"Generalizable Targeted Data Poisoning against Varying Physical Objects","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-11T22:05:21.603490Z"},"links":{"citing_paper":"/paper/2412.03908"},"observation_digest":"sha256:1eba4c70467e34f345917c5e6cd0d0347421783b4e6e515f3bcfd4033b81d777","observation_id":"80eeaf3d-9c79-4b15-b1e7-ab7d0e5edd24","resolution":{"observed_at":"2026-08-11T22:05:21.907357Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:05:21.607812Z","title":"Fooling automated surveillance cameras: adversarial patches to at- tack person detection","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.03908","last_updated":"2025-07-26T03:30:55Z","snapshot_observed_at":"2026-08-11T21:55:21.186265Z","submitted_at":"2024-12-05T06:27:14Z","title":"Generalizable Targeted Data Poisoning against Varying Physical Objects","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-11T22:05:21.607812Z"},"links":{"citing_paper":"/paper/2412.03908"},"observation_digest":"sha256:4b1efa972e730853250a1b3c54928da6187a28e1acd8a08d50cf37f5b7307da0","observation_id":"b3cc0417-1d1b-465f-a7f7-815c11c8d3f7","resolution":{"observed_at":"2026-08-11T22:05:21.607812Z","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":"2026-08-11T22:05:21.874241Z","title":"The caltech-ucsd birds-200-2011 dataset, 2011","venue":null,"work_id":"f62696fb-17fa-4c0a-8e7e-5d5100ef5871","year":2011},"citing_paper":{"arxiv_id":"2412.03908","last_updated":"2025-07-26T03:30:55Z","snapshot_observed_at":"2026-08-11T21:55:21.186265Z","submitted_at":"2024-12-05T06:27:14Z","title":"Generalizable Targeted Data Poisoning against Varying Physical Objects","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-11T22:05:21.611725Z"},"links":{"citing_paper":"/paper/2412.03908"},"observation_digest":"sha256:1edba0bca410548b6a576b5ac97fc18d3e4f53aff88d1ad8104b7bd9bce02a75","observation_id":"9b2c3b6a-f0a3-42a2-a7d9-a363f7bc5701","resolution":{"observed_at":"2026-08-11T22:05:21.879335Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:05:21.858808Z","title":"Provably unlearnable data examples","venue":null,"work_id":"20a8633b-f8ac-47e0-ab77-0671f175bd58","year":2025},"citing_paper":{"arxiv_id":"2412.03908","last_updated":"2025-07-26T03:30:55Z","snapshot_observed_at":"2026-08-11T21:55:21.186265Z","submitted_at":"2024-12-05T06:27:14Z","title":"Generalizable Targeted Data Poisoning against Varying Physical Objects","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-11T22:05:21.615743Z"},"links":{"citing_paper":"/paper/2412.03908"},"observation_digest":"sha256:e48219778b34b27935bcb81da27596bbf1672dfd2571698804317b63ae918699","observation_id":"d2d2175e-99e7-4ded-b178-c0072dd12f10","resolution":{"observed_at":"2026-08-11T22:05:21.863715Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:05:21.844576Z","title":"Backdoor attacks against deep learning systems in the physical world","venue":null,"work_id":"bdfac68c-bd30-40f3-beac-21aa5fdc966e","year":2021},"citing_paper":{"arxiv_id":"2412.03908","last_updated":"2025-07-26T03:30:55Z","snapshot_observed_at":"2026-08-11T21:55:21.186265Z","submitted_at":"2024-12-05T06:27:14Z","title":"Generalizable Targeted Data Poisoning against Varying Physical Objects","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-11T22:05:21.620459Z"},"links":{"citing_paper":"/paper/2412.03908"},"observation_digest":"sha256:fedf621af7214986170c8d42d48f8e8cbbab8ef057fca2a9efcd31f1035ff539","observation_id":"936c15cb-ce48-4ac6-a8d2-6b63e6f20d97","resolution":{"observed_at":"2026-08-11T22:05:21.848908Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.10673","last_updated":"2022-06-21T18:52:25Z","snapshot_observed_at":"2026-07-06T13:23:18.665282Z","submitted_at":"2022-06-21T18:52:25Z","title":"Natural Backdoor Datasets","version":1},"cited_work":{"arxiv_id":"2206.10673","doi":null,"metadata_source":"pith","pith_arxiv_id":"2206.10673","snapshot_observed_at":"2026-08-11T22:05:21.695419Z","title":"Natural Backdoor Datasets","venue":"cs.CV","work_id":"e2d7ccbe-f140-4549-a7c3-5b2c3c8e31fe","year":2022},"citing_paper":{"arxiv_id":"2412.03908","last_updated":"2025-07-26T03:30:55Z","snapshot_observed_at":"2026-08-11T21:55:21.186265Z","submitted_at":"2024-12-05T06:27:14Z","title":"Generalizable Targeted Data Poisoning against Varying Physical Objects","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-11T22:05:21.625002Z"},"links":{"cited_paper":"/paper/2206.10673","citing_paper":"/paper/2412.03908"},"observation_digest":"sha256:82e17532f8e749d324c392ab461528686134e3641689cffd32234b0f0688f09d","observation_id":"ebde6ed6-cc6d-4643-b6a2-1429b1d7c53d","resolution":{"observed_at":"2026-08-11T22:05:21.701243Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:05:21.830813Z","title":"Making an invisibility cloak: Real world adversar- ial attacks on object detectors","venue":null,"work_id":"38a6743d-4878-42bf-bc35-23742771b310","year":2020},"citing_paper":{"arxiv_id":"2412.03908","last_updated":"2025-07-26T03:30:55Z","snapshot_observed_at":"2026-08-11T21:55:21.186265Z","submitted_at":"2024-12-05T06:27:14Z","title":"Generalizable Targeted Data Poisoning against Varying Physical Objects","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-11T22:05:21.630297Z"},"links":{"citing_paper":"/paper/2412.03908"},"observation_digest":"sha256:66dfab18838d94dddbc5782e1e2fab06d2220a1cd898fa2276f478033b9b5173","observation_id":"6c2c7ee5-7c99-4ce2-be1d-18e59cc925f1","resolution":{"observed_at":"2026-08-11T22:05:21.835168Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:05:21.816297Z","title":"Adversarial la- bel flips attack on support vector machines","venue":null,"work_id":"43692d9b-98d6-4302-81fa-1a2aec0b1f82","year":2012},"citing_paper":{"arxiv_id":"2412.03908","last_updated":"2025-07-26T03:30:55Z","snapshot_observed_at":"2026-08-11T21:55:21.186265Z","submitted_at":"2024-12-05T06:27:14Z","title":"Generalizable Targeted Data Poisoning against Varying Physical Objects","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-11T22:05:21.635239Z"},"links":{"citing_paper":"/paper/2412.03908"},"observation_digest":"sha256:78e57c0f97ba44d09d8a4e489ade5c4d1ddf01542fe9735606a90e65e80847c4","observation_id":"f397940c-65c3-4c3f-8e91-36c511dbd587","resolution":{"observed_at":"2026-08-11T22:05:21.820992Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:05:21.639745Z","title":"Adversarial t-shirt! evading person detectors in a physical world","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.03908","last_updated":"2025-07-26T03:30:55Z","snapshot_observed_at":"2026-08-11T21:55:21.186265Z","submitted_at":"2024-12-05T06:27:14Z","title":"Generalizable Targeted Data Poisoning against Varying Physical Objects","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-11T22:05:21.639745Z"},"links":{"citing_paper":"/paper/2412.03908"},"observation_digest":"sha256:3f6aa44c37c71f99d3eb5094ffc00a336a750e8f6c3fe8ba92cb679480d36e0c","observation_id":"529a7a72-1625-444c-8c65-3c0f04372fc7","resolution":{"observed_at":"2026-08-11T22:05:21.639745Z","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":"2026-08-11T22:05:21.791903Z","title":"Not all poisons are created equal: Robust training against data poi- soning","venue":null,"work_id":"9fc3e41a-10f4-4691-89ad-7e47ce942dd5","year":2022},"citing_paper":{"arxiv_id":"2412.03908","last_updated":"2025-07-26T03:30:55Z","snapshot_observed_at":"2026-08-11T21:55:21.186265Z","submitted_at":"2024-12-05T06:27:14Z","title":"Generalizable Targeted Data Poisoning against Varying Physical Objects","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-11T22:05:21.644279Z"},"links":{"citing_paper":"/paper/2412.03908"},"observation_digest":"sha256:6441b7855a4c502da74b5231ded6bb169209a37de191a158d9f6ad2f34900f0c","observation_id":"091ad006-a960-4ad5-b9cb-ef50f80d4046","resolution":{"observed_at":"2026-08-11T22:05:21.796817Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:05:21.775968Z","title":"Latent backdoor attacks on deep neural networks","venue":null,"work_id":"318e9b98-7d75-424f-a692-d706ce28f153","year":2019},"citing_paper":{"arxiv_id":"2412.03908","last_updated":"2025-07-26T03:30:55Z","snapshot_observed_at":"2026-08-11T21:55:21.186265Z","submitted_at":"2024-12-05T06:27:14Z","title":"Generalizable Targeted Data Poisoning against Varying Physical Objects","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-11T22:05:21.649021Z"},"links":{"citing_paper":"/paper/2412.03908"},"observation_digest":"sha256:f335d8e006640a7b89778c6cb07fd2d4e1391fbf0bc0e09f7831761b06acd99a","observation_id":"dd1e103f-8109-42c6-8a63-56ccd1f9d9cc","resolution":{"observed_at":"2026-08-11T22:05:21.781129Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:05:21.759499Z","title":"Transferable clean- label poisoning attacks on deep neural nets","venue":null,"work_id":"1ce85830-4e1b-4a12-aa6c-0fa750647e51","year":null},"citing_paper":{"arxiv_id":"2412.03908","last_updated":"2025-07-26T03:30:55Z","snapshot_observed_at":"2026-08-11T21:55:21.186265Z","submitted_at":"2024-12-05T06:27:14Z","title":"Generalizable Targeted Data Poisoning against Varying Physical Objects","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-11T22:05:21.654010Z"},"links":{"citing_paper":"/paper/2412.03908"},"observation_digest":"sha256:7a47cc78adeafe969fc7e6a2cca89aa7f2f6c56c13bb7bdecbe1862ba34df5d1","observation_id":"c7e06f8f-7043-4fb2-8144-518a2e2e6fd9","resolution":{"observed_at":"2026-08-11T22:05:21.765244Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:05:21.743994Z","title":"sports car","venue":null,"work_id":"259705f4-9245-42e6-a6a4-7d7a6c99ba2b","year":null},"citing_paper":{"arxiv_id":"2412.03908","last_updated":"2025-07-26T03:30:55Z","snapshot_observed_at":"2026-08-11T21:55:21.186265Z","submitted_at":"2024-12-05T06:27:14Z","title":"Generalizable Targeted Data Poisoning against Varying Physical Objects","version":2},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-11T22:05:21.658856Z"},"links":{"citing_paper":"/paper/2412.03908"},"observation_digest":"sha256:2f3a0b6d6f3b0bbe3f4f63f615738b3204fcbfa1135d0ab45007ff7bb336ebf5","observation_id":"59b3864e-ffa1-41ab-8bfd-25cc995fb013","resolution":{"observed_at":"2026-08-11T22:05:21.748903Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2412.03908","last_updated":"2025-07-26T03:30:55Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-11T21:55:21.186265Z","submitted_at":"2024-12-05T06:27:14Z","title":"Generalizable Targeted Data Poisoning against Varying Physical Objects"},"reference_resolution":{"displayed":44,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":9,"verified_exact":1,"verified_fuzzy":34},"total_outbound_references":44},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"thesis":"As of 13 August 2026, this Paper Citation Record lists 44 of 44 outbound references and 0 inbound Pith citation observations for arXiv:2412.03908."}