{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:NMLHH7NPKARD6KUQOO6EQQEOX2","short_pith_number":"pith:NMLHH7NP","schema_version":"1.0","canonical_sha256":"6b1673fdaf50223f2a9073bc48408ebe950d24424aeaa7d976f08ed6dc9cb3f3","source":{"kind":"arxiv","id":"1806.02299","version":4},"attestation_state":"computed","paper":{"title":"DPatch: An Adversarial Patch Attack on Object Detectors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Hai Li, Huanrui Yang, Linghao Song, Xin Liu, Yiran Chen, Ziwei Liu","submitted_at":"2018-06-05T17:04:37Z","abstract_excerpt":"Object detectors have emerged as an indispensable module in modern computer vision systems. In this work, we propose DPatch -- a black-box adversarial-patch-based attack towards mainstream object detectors (i.e. Faster R-CNN and YOLO). Unlike the original adversarial patch that only manipulates image-level classifier, our DPatch simultaneously attacks the bounding box regression and object classification so as to disable their predictions. Compared to prior works, DPatch has several appealing properties: (1) DPatch can perform both untargeted and targeted effective attacks, degrading the mAP o"},"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":"1806.02299","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-06-05T17:04:37Z","cross_cats_sorted":["cs.CR","cs.LG"],"title_canon_sha256":"2f74945382171a26c51e9ac7305c2830807040d4cc9532e29dbdb789697b8e7c","abstract_canon_sha256":"1b8f04ad5d4b3421302fa84fd5b3b67f581592adaa073af10f7ce85d5f5785d5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:47:53.914218Z","signature_b64":"wMf3sBkiigH8frlFSztatKh0SjWL/pCr8TNg/wP6+1EHHTGsMsw3u+kLOt6Wh0J+DIpsDJQ2F45otvwLgSOdCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b1673fdaf50223f2a9073bc48408ebe950d24424aeaa7d976f08ed6dc9cb3f3","last_reissued_at":"2026-05-17T23:47:53.913617Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:47:53.913617Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DPatch: An Adversarial Patch Attack on Object Detectors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Hai Li, Huanrui Yang, Linghao Song, Xin Liu, Yiran Chen, Ziwei Liu","submitted_at":"2018-06-05T17:04:37Z","abstract_excerpt":"Object detectors have emerged as an indispensable module in modern computer vision systems. In this work, we propose DPatch -- a black-box adversarial-patch-based attack towards mainstream object detectors (i.e. Faster R-CNN and YOLO). Unlike the original adversarial patch that only manipulates image-level classifier, our DPatch simultaneously attacks the bounding box regression and object classification so as to disable their predictions. Compared to prior works, DPatch has several appealing properties: (1) DPatch can perform both untargeted and targeted effective attacks, degrading the mAP o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.02299","kind":"arxiv","version":4},"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":"1806.02299","created_at":"2026-05-17T23:47:53.913707+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.02299v4","created_at":"2026-05-17T23:47:53.913707+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.02299","created_at":"2026-05-17T23:47:53.913707+00:00"},{"alias_kind":"pith_short_12","alias_value":"NMLHH7NPKARD","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_16","alias_value":"NMLHH7NPKARD6KUQ","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_8","alias_value":"NMLHH7NP","created_at":"2026-05-18T12:32:40.477152+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"1906.11897","citing_title":"On Physical Adversarial Patches for Object Detection","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"1907.10310","citing_title":"Towards Adversarially Robust Object Detection","ref_index":31,"is_internal_anchor":true},{"citing_arxiv_id":"2511.09829","citing_title":"Thermally Activated Dual-Modal Adversarial Clothing against AI Surveillance Systems","ref_index":42,"is_internal_anchor":true},{"citing_arxiv_id":"2512.03730","citing_title":"Out-of-the-box: Black-box Causal Attacks on Object Detectors","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2604.02457","citing_title":"Street-Legal Physical-World Adversarial Rim for License Plates","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12418","citing_title":"RACF: A Resilient Autonomous Car Framework with Object Distance Correction","ref_index":8,"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":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NMLHH7NPKARD6KUQOO6EQQEOX2","json":"https://pith.science/pith/NMLHH7NPKARD6KUQOO6EQQEOX2.json","graph_json":"https://pith.science/api/pith-number/NMLHH7NPKARD6KUQOO6EQQEOX2/graph.json","events_json":"https://pith.science/api/pith-number/NMLHH7NPKARD6KUQOO6EQQEOX2/events.json","paper":"https://pith.science/paper/NMLHH7NP"},"agent_actions":{"view_html":"https://pith.science/pith/NMLHH7NPKARD6KUQOO6EQQEOX2","download_json":"https://pith.science/pith/NMLHH7NPKARD6KUQOO6EQQEOX2.json","view_paper":"https://pith.science/paper/NMLHH7NP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.02299&json=true","fetch_graph":"https://pith.science/api/pith-number/NMLHH7NPKARD6KUQOO6EQQEOX2/graph.json","fetch_events":"https://pith.science/api/pith-number/NMLHH7NPKARD6KUQOO6EQQEOX2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NMLHH7NPKARD6KUQOO6EQQEOX2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NMLHH7NPKARD6KUQOO6EQQEOX2/action/storage_attestation","attest_author":"https://pith.science/pith/NMLHH7NPKARD6KUQOO6EQQEOX2/action/author_attestation","sign_citation":"https://pith.science/pith/NMLHH7NPKARD6KUQOO6EQQEOX2/action/citation_signature","submit_replication":"https://pith.science/pith/NMLHH7NPKARD6KUQOO6EQQEOX2/action/replication_record"}},"created_at":"2026-05-17T23:47:53.913707+00:00","updated_at":"2026-05-17T23:47:53.913707+00:00"}