{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GVEYNBGAC5K4MHZSCQASV3WHRO","short_pith_number":"pith:GVEYNBGA","schema_version":"1.0","canonical_sha256":"35498684c01755c61f3214012aeec78ba18a3536e4bd149cf77e00b9ef7a41ea","source":{"kind":"arxiv","id":"2309.08953","version":1},"attestation_state":"computed","paper":{"title":"Robust Backdoor Attacks on Object Detection in Real World","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Wang, Boyuan Ji, Shenhui Huang, Shuke He, Wei Wang, Xiang Ling, Yaguan Qian","submitted_at":"2023-09-16T11:09:08Z","abstract_excerpt":"Deep learning models are widely deployed in many applications, such as object detection in various security fields. However, these models are vulnerable to backdoor attacks. Most backdoor attacks were intensively studied on classified models, but little on object detection. Previous works mainly focused on the backdoor attack in the digital world, but neglect the real world. Especially, the backdoor attack's effect in the real world will be easily influenced by physical factors like distance and illumination. In this paper, we proposed a variable-size backdoor trigger to adapt to the different"},"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":"2309.08953","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-16T11:09:08Z","cross_cats_sorted":[],"title_canon_sha256":"d6270fd132b127633af7dcfd77c28a07a067cf96b7cfc6fa8edff71e55bf0644","abstract_canon_sha256":"861a2349fcd132067d003894d0fb0c4d8c0935c4aa6ebc99693e9d01a428103e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:51:32.091817Z","signature_b64":"odqoXRON8BQEU7lWWisiOD7PI9Iv07K0L1O9Zwh+tGXFBWRRrBPGvBio43qwCXPAvEJdq7UaNKRsax6w5ewbAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"35498684c01755c61f3214012aeec78ba18a3536e4bd149cf77e00b9ef7a41ea","last_reissued_at":"2026-07-05T06:51:32.091387Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:51:32.091387Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust Backdoor Attacks on Object Detection in Real World","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Wang, Boyuan Ji, Shenhui Huang, Shuke He, Wei Wang, Xiang Ling, Yaguan Qian","submitted_at":"2023-09-16T11:09:08Z","abstract_excerpt":"Deep learning models are widely deployed in many applications, such as object detection in various security fields. However, these models are vulnerable to backdoor attacks. Most backdoor attacks were intensively studied on classified models, but little on object detection. Previous works mainly focused on the backdoor attack in the digital world, but neglect the real world. Especially, the backdoor attack's effect in the real world will be easily influenced by physical factors like distance and illumination. In this paper, we proposed a variable-size backdoor trigger to adapt to the different"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.08953","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/2309.08953/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":"2309.08953","created_at":"2026-07-05T06:51:32.091454+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.08953v1","created_at":"2026-07-05T06:51:32.091454+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.08953","created_at":"2026-07-05T06:51:32.091454+00:00"},{"alias_kind":"pith_short_12","alias_value":"GVEYNBGAC5K4","created_at":"2026-07-05T06:51:32.091454+00:00"},{"alias_kind":"pith_short_16","alias_value":"GVEYNBGAC5K4MHZS","created_at":"2026-07-05T06:51:32.091454+00:00"},{"alias_kind":"pith_short_8","alias_value":"GVEYNBGA","created_at":"2026-07-05T06:51:32.091454+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.16154","citing_title":"BadDepth: Backdoor Attacks Against Monocular Depth Estimation in the Physical World","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GVEYNBGAC5K4MHZSCQASV3WHRO","json":"https://pith.science/pith/GVEYNBGAC5K4MHZSCQASV3WHRO.json","graph_json":"https://pith.science/api/pith-number/GVEYNBGAC5K4MHZSCQASV3WHRO/graph.json","events_json":"https://pith.science/api/pith-number/GVEYNBGAC5K4MHZSCQASV3WHRO/events.json","paper":"https://pith.science/paper/GVEYNBGA"},"agent_actions":{"view_html":"https://pith.science/pith/GVEYNBGAC5K4MHZSCQASV3WHRO","download_json":"https://pith.science/pith/GVEYNBGAC5K4MHZSCQASV3WHRO.json","view_paper":"https://pith.science/paper/GVEYNBGA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.08953&json=true","fetch_graph":"https://pith.science/api/pith-number/GVEYNBGAC5K4MHZSCQASV3WHRO/graph.json","fetch_events":"https://pith.science/api/pith-number/GVEYNBGAC5K4MHZSCQASV3WHRO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GVEYNBGAC5K4MHZSCQASV3WHRO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GVEYNBGAC5K4MHZSCQASV3WHRO/action/storage_attestation","attest_author":"https://pith.science/pith/GVEYNBGAC5K4MHZSCQASV3WHRO/action/author_attestation","sign_citation":"https://pith.science/pith/GVEYNBGAC5K4MHZSCQASV3WHRO/action/citation_signature","submit_replication":"https://pith.science/pith/GVEYNBGAC5K4MHZSCQASV3WHRO/action/replication_record"}},"created_at":"2026-07-05T06:51:32.091454+00:00","updated_at":"2026-07-05T06:51:32.091454+00:00"}