{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:4IAX4I57NUCQNRCBKPIIIZYDRM","short_pith_number":"pith:4IAX4I57","schema_version":"1.0","canonical_sha256":"e2017e23bf6d0506c44153d08467038b2479ab8bd1aa39827b4fa8fad83c37bd","source":{"kind":"arxiv","id":"2201.08970","version":1},"attestation_state":"computed","paper":{"title":"Parallel Rectangle Flip Attack: A Query-based Black-box Attack against Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baoyuan Wu, Siyuan Liang, Xiaochun Cao, Xingxing Wei, Yanbo Fan","submitted_at":"2022-01-22T06:00:17Z","abstract_excerpt":"Object detection has been widely used in many safety-critical tasks, such as autonomous driving. However, its vulnerability to adversarial examples has not been sufficiently studied, especially under the practical scenario of black-box attacks, where the attacker can only access the query feedback of predicted bounding-boxes and top-1 scores returned by the attacked model. Compared with black-box attack to image classification, there are two main challenges in black-box attack to detection. Firstly, even if one bounding-box is successfully attacked, another sub-optimal bounding-box may be dete"},"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":"2201.08970","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-01-22T06:00:17Z","cross_cats_sorted":[],"title_canon_sha256":"0747044c8e4c6189e1333545ec19bff210dc14aca34ed011ce44ebdee9982fd4","abstract_canon_sha256":"4612ed4732f1cc16873804ad3f0090b9e13d560daf9b856906749ab84c1f6b03"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:50:38.914665Z","signature_b64":"2O+9hjWT2VGIcoKlShNF0ptcDBfZFpqrLnKyhBjUHQeiSQkzwQoP0w3Yk9FEl6hYD7fg1QSt6GzeguagfQnaBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e2017e23bf6d0506c44153d08467038b2479ab8bd1aa39827b4fa8fad83c37bd","last_reissued_at":"2026-07-05T03:50:38.914143Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:50:38.914143Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Parallel Rectangle Flip Attack: A Query-based Black-box Attack against Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baoyuan Wu, Siyuan Liang, Xiaochun Cao, Xingxing Wei, Yanbo Fan","submitted_at":"2022-01-22T06:00:17Z","abstract_excerpt":"Object detection has been widely used in many safety-critical tasks, such as autonomous driving. However, its vulnerability to adversarial examples has not been sufficiently studied, especially under the practical scenario of black-box attacks, where the attacker can only access the query feedback of predicted bounding-boxes and top-1 scores returned by the attacked model. Compared with black-box attack to image classification, there are two main challenges in black-box attack to detection. Firstly, even if one bounding-box is successfully attacked, another sub-optimal bounding-box may be dete"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.08970","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2201.08970/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2201.08970","created_at":"2026-07-05T03:50:38.914200+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.08970v1","created_at":"2026-07-05T03:50:38.914200+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.08970","created_at":"2026-07-05T03:50:38.914200+00:00"},{"alias_kind":"pith_short_12","alias_value":"4IAX4I57NUCQ","created_at":"2026-07-05T03:50:38.914200+00:00"},{"alias_kind":"pith_short_16","alias_value":"4IAX4I57NUCQNRCB","created_at":"2026-07-05T03:50:38.914200+00:00"},{"alias_kind":"pith_short_8","alias_value":"4IAX4I57","created_at":"2026-07-05T03:50:38.914200+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05783","citing_title":"Benchmarking the Robustness of Autonomous Driving to Environmental Illusions: A Lane Perception Perspective","ref_index":82,"is_internal_anchor":true},{"citing_arxiv_id":"2606.18318","citing_title":"Budget-Aware Adaptive Adversarial Patches for Black-Box Object Detection","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23220","citing_title":"WMAttack: Automated Attack Search for Adversarial Evaluation of World-Model Agents","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2411.18275","citing_title":"Visual Adversarial Attack on Vision-Language Models for Autonomous Driving","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04488","citing_title":"A Patch-based Cross-view Regularized Framework for Backdoor Defense in Multimodal Large Language Models","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04630","citing_title":"Multimodal Backdoor Attack on VLMs for Autonomous Driving via Graffiti and Cross-Lingual Triggers","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4IAX4I57NUCQNRCBKPIIIZYDRM","json":"https://pith.science/pith/4IAX4I57NUCQNRCBKPIIIZYDRM.json","graph_json":"https://pith.science/api/pith-number/4IAX4I57NUCQNRCBKPIIIZYDRM/graph.json","events_json":"https://pith.science/api/pith-number/4IAX4I57NUCQNRCBKPIIIZYDRM/events.json","paper":"https://pith.science/paper/4IAX4I57"},"agent_actions":{"view_html":"https://pith.science/pith/4IAX4I57NUCQNRCBKPIIIZYDRM","download_json":"https://pith.science/pith/4IAX4I57NUCQNRCBKPIIIZYDRM.json","view_paper":"https://pith.science/paper/4IAX4I57","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.08970&json=true","fetch_graph":"https://pith.science/api/pith-number/4IAX4I57NUCQNRCBKPIIIZYDRM/graph.json","fetch_events":"https://pith.science/api/pith-number/4IAX4I57NUCQNRCBKPIIIZYDRM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4IAX4I57NUCQNRCBKPIIIZYDRM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4IAX4I57NUCQNRCBKPIIIZYDRM/action/storage_attestation","attest_author":"https://pith.science/pith/4IAX4I57NUCQNRCBKPIIIZYDRM/action/author_attestation","sign_citation":"https://pith.science/pith/4IAX4I57NUCQNRCBKPIIIZYDRM/action/citation_signature","submit_replication":"https://pith.science/pith/4IAX4I57NUCQNRCBKPIIIZYDRM/action/replication_record"}},"created_at":"2026-07-05T03:50:38.914200+00:00","updated_at":"2026-07-05T03:50:38.914200+00:00"}