{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:KBGOF4VYCYRXTCI47XGQ2CFVP3","short_pith_number":"pith:KBGOF4VY","schema_version":"1.0","canonical_sha256":"504ce2f2b8162379891cfdcd0d08b57efb030720ba04df02afcd055c2a01f7f6","source":{"kind":"arxiv","id":"2209.02339","version":2},"attestation_state":"computed","paper":{"title":"TransCAB: Transferable Clean-Annotation Backdoor to Object Detection with Natural Trigger in Real-World","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.CV","authors_text":"Alsharif Abuadbba, Anmin Fu, Derek Abbott, Hua Ma, Nepal Surya, Said F. Al-Sarawi, Yansong Gao, Yinshan Li, Zhi Zhang","submitted_at":"2022-09-06T09:56:33Z","abstract_excerpt":"Object detection is the foundation of various critical computer-vision tasks such as segmentation, object tracking, and event detection. To train an object detector with satisfactory accuracy, a large amount of data is required. However, due to the intensive workforce involved with annotating large datasets, such a data curation task is often outsourced to a third party or relied on volunteers. This work reveals severe vulnerabilities of such data curation pipeline. We propose MACAB that crafts clean-annotated images to stealthily implant the backdoor into the object detectors trained on them "},"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":"2209.02339","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-09-06T09:56:33Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"72d873410c5457f4fa8c01366c7a12a4728e1332bb25a1f0e02ed808013d8854","abstract_canon_sha256":"7969ae88db64037c53cc16a2ab96f398aa97b1e211f400b117279dd1f8742cd3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:47:00.272422Z","signature_b64":"Iez4bnU1+HdC5FzDdNHmbA0TKYf7qWLryKYcY9Gzl3D8x+EkzhVpnc4VPHLVj6kXRZG/YN40qF1XZ9FfZJX6AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"504ce2f2b8162379891cfdcd0d08b57efb030720ba04df02afcd055c2a01f7f6","last_reissued_at":"2026-07-05T06:47:00.271942Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:47:00.271942Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TransCAB: Transferable Clean-Annotation Backdoor to Object Detection with Natural Trigger in Real-World","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.CV","authors_text":"Alsharif Abuadbba, Anmin Fu, Derek Abbott, Hua Ma, Nepal Surya, Said F. Al-Sarawi, Yansong Gao, Yinshan Li, Zhi Zhang","submitted_at":"2022-09-06T09:56:33Z","abstract_excerpt":"Object detection is the foundation of various critical computer-vision tasks such as segmentation, object tracking, and event detection. To train an object detector with satisfactory accuracy, a large amount of data is required. However, due to the intensive workforce involved with annotating large datasets, such a data curation task is often outsourced to a third party or relied on volunteers. This work reveals severe vulnerabilities of such data curation pipeline. We propose MACAB that crafts clean-annotated images to stealthily implant the backdoor into the object detectors trained on them "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.02339","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2209.02339/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":"2209.02339","created_at":"2026-07-05T06:47:00.271994+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.02339v2","created_at":"2026-07-05T06:47:00.271994+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.02339","created_at":"2026-07-05T06:47:00.271994+00:00"},{"alias_kind":"pith_short_12","alias_value":"KBGOF4VYCYRX","created_at":"2026-07-05T06:47:00.271994+00:00"},{"alias_kind":"pith_short_16","alias_value":"KBGOF4VYCYRXTCI4","created_at":"2026-07-05T06:47:00.271994+00:00"},{"alias_kind":"pith_short_8","alias_value":"KBGOF4VY","created_at":"2026-07-05T06:47:00.271994+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.15439","citing_title":"Twin Trigger Generative Networks for Backdoor Attacks against Object Detection","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KBGOF4VYCYRXTCI47XGQ2CFVP3","json":"https://pith.science/pith/KBGOF4VYCYRXTCI47XGQ2CFVP3.json","graph_json":"https://pith.science/api/pith-number/KBGOF4VYCYRXTCI47XGQ2CFVP3/graph.json","events_json":"https://pith.science/api/pith-number/KBGOF4VYCYRXTCI47XGQ2CFVP3/events.json","paper":"https://pith.science/paper/KBGOF4VY"},"agent_actions":{"view_html":"https://pith.science/pith/KBGOF4VYCYRXTCI47XGQ2CFVP3","download_json":"https://pith.science/pith/KBGOF4VYCYRXTCI47XGQ2CFVP3.json","view_paper":"https://pith.science/paper/KBGOF4VY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.02339&json=true","fetch_graph":"https://pith.science/api/pith-number/KBGOF4VYCYRXTCI47XGQ2CFVP3/graph.json","fetch_events":"https://pith.science/api/pith-number/KBGOF4VYCYRXTCI47XGQ2CFVP3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KBGOF4VYCYRXTCI47XGQ2CFVP3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KBGOF4VYCYRXTCI47XGQ2CFVP3/action/storage_attestation","attest_author":"https://pith.science/pith/KBGOF4VYCYRXTCI47XGQ2CFVP3/action/author_attestation","sign_citation":"https://pith.science/pith/KBGOF4VYCYRXTCI47XGQ2CFVP3/action/citation_signature","submit_replication":"https://pith.science/pith/KBGOF4VYCYRXTCI47XGQ2CFVP3/action/replication_record"}},"created_at":"2026-07-05T06:47:00.271994+00:00","updated_at":"2026-07-05T06:47:00.271994+00:00"}