{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:FQ7KEVPJAOUIVJZWBORRTT5SOW","short_pith_number":"pith:FQ7KEVPJ","schema_version":"1.0","canonical_sha256":"2c3ea255e903a88aa7360ba319cfb27589970a1b418aa7f30bc7ba06033831f3","source":{"kind":"arxiv","id":"1712.09665","version":2},"attestation_state":"computed","paper":{"title":"Adversarial Patch","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aurko Roy, Dandelion Man\\'e, Justin Gilmer, Mart\\'in Abadi, Tom B. Brown","submitted_at":"2017-12-27T20:03:51Z","abstract_excerpt":"We present a method to create universal, robust, targeted adversarial image patches in the real world. The patches are universal because they can be used to attack any scene, robust because they work under a wide variety of transformations, and targeted because they can cause a classifier to output any target class. These adversarial patches can be printed, added to any scene, photographed, and presented to image classifiers; even when the patches are small, they cause the classifiers to ignore the other items in the scene and report a chosen target class.\n  To reproduce the results from the p"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1712.09665","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-12-27T20:03:51Z","cross_cats_sorted":[],"title_canon_sha256":"00fe2887bb7edd213ea60b7debc2f289307e59f0e55a2118a2c8d68d1fbed18f","abstract_canon_sha256":"173922f051ebc49909e61a4901581e0fdd13bc237fa3b144a57151e0afc79149"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:15:46.764874Z","signature_b64":"V6a4ELj5Fmcg6aA9mSk2PDNeMSDql0FituWjE6gWjZ5Ipk+SOTOhvhTyCEnvA9SjWhFEFt/o/MhOWnsl0GGsAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c3ea255e903a88aa7360ba319cfb27589970a1b418aa7f30bc7ba06033831f3","last_reissued_at":"2026-05-18T00:15:46.762735Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:15:46.762735Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adversarial Patch","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aurko Roy, Dandelion Man\\'e, Justin Gilmer, Mart\\'in Abadi, Tom B. Brown","submitted_at":"2017-12-27T20:03:51Z","abstract_excerpt":"We present a method to create universal, robust, targeted adversarial image patches in the real world. The patches are universal because they can be used to attack any scene, robust because they work under a wide variety of transformations, and targeted because they can cause a classifier to output any target class. These adversarial patches can be printed, added to any scene, photographed, and presented to image classifiers; even when the patches are small, they cause the classifiers to ignore the other items in the scene and report a chosen target class.\n  To reproduce the results from the p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.09665","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1712.09665","created_at":"2026-05-18T00:15:46.762865+00:00"},{"alias_kind":"arxiv_version","alias_value":"1712.09665v2","created_at":"2026-05-18T00:15:46.762865+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.09665","created_at":"2026-05-18T00:15:46.762865+00:00"},{"alias_kind":"pith_short_12","alias_value":"FQ7KEVPJAOUI","created_at":"2026-05-18T12:31:15.632608+00:00"},{"alias_kind":"pith_short_16","alias_value":"FQ7KEVPJAOUIVJZW","created_at":"2026-05-18T12:31:15.632608+00:00"},{"alias_kind":"pith_short_8","alias_value":"FQ7KEVPJ","created_at":"2026-05-18T12:31:15.632608+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2511.09829","citing_title":"Thermally Activated Dual-Modal Adversarial Clothing against AI Surveillance Systems","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2604.02457","citing_title":"Street-Legal Physical-World Adversarial Rim for License Plates","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27414","citing_title":"Understanding Adversarial Transferability in Vision-Language Models for Autonomous Driving: A Cross-Architecture Analysis","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23105","citing_title":"Transferable Physical-World Adversarial Patches Against Object Detection in Autonomous Driving","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22552","citing_title":"Transferable Physical-World Adversarial Patches Against Pedestrian Detection Models","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01950","citing_title":"TRAP: Tail-aware Ranking Attack for World-Model Planning","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12418","citing_title":"RACF: A Resilient Autonomous Car Framework with Object Distance Correction","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06865","citing_title":"Physical Adversarial Attacks on AI Surveillance Systems:Detection, Tracking, and Visible--Infrared Evasion","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FQ7KEVPJAOUIVJZWBORRTT5SOW","json":"https://pith.science/pith/FQ7KEVPJAOUIVJZWBORRTT5SOW.json","graph_json":"https://pith.science/api/pith-number/FQ7KEVPJAOUIVJZWBORRTT5SOW/graph.json","events_json":"https://pith.science/api/pith-number/FQ7KEVPJAOUIVJZWBORRTT5SOW/events.json","paper":"https://pith.science/paper/FQ7KEVPJ"},"agent_actions":{"view_html":"https://pith.science/pith/FQ7KEVPJAOUIVJZWBORRTT5SOW","download_json":"https://pith.science/pith/FQ7KEVPJAOUIVJZWBORRTT5SOW.json","view_paper":"https://pith.science/paper/FQ7KEVPJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1712.09665&json=true","fetch_graph":"https://pith.science/api/pith-number/FQ7KEVPJAOUIVJZWBORRTT5SOW/graph.json","fetch_events":"https://pith.science/api/pith-number/FQ7KEVPJAOUIVJZWBORRTT5SOW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FQ7KEVPJAOUIVJZWBORRTT5SOW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FQ7KEVPJAOUIVJZWBORRTT5SOW/action/storage_attestation","attest_author":"https://pith.science/pith/FQ7KEVPJAOUIVJZWBORRTT5SOW/action/author_attestation","sign_citation":"https://pith.science/pith/FQ7KEVPJAOUIVJZWBORRTT5SOW/action/citation_signature","submit_replication":"https://pith.science/pith/FQ7KEVPJAOUIVJZWBORRTT5SOW/action/replication_record"}},"created_at":"2026-05-18T00:15:46.762865+00:00","updated_at":"2026-05-18T00:15:46.762865+00:00"}