{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KPEZNRII7EGUSL2P4Q6K6WCIUL","short_pith_number":"pith:KPEZNRII","schema_version":"1.0","canonical_sha256":"53c996c508f90d492f4fe43caf5848a2eaeb8a023185d7f383da2fbf0f285133","source":{"kind":"arxiv","id":"2411.15439","version":1},"attestation_state":"computed","paper":{"title":"Twin Trigger Generative Networks for Backdoor Attacks against Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guanggang Geng, Jian Weng, Shreyank N Gowda, Shuyuan Lin, Xiaobo Jin, Zhi Liu, Zhiying Li","submitted_at":"2024-11-23T03:46:45Z","abstract_excerpt":"Object detectors, which are widely used in real-world applications, are vulnerable to backdoor attacks. This vulnerability arises because many users rely on datasets or pre-trained models provided by third parties due to constraints on data and resources. However, most research on backdoor attacks has focused on image classification, with limited investigation into object detection. Furthermore, the triggers for most existing backdoor attacks on object detection are manually generated, requiring prior knowledge and consistent patterns between the training and inference stages. This approach ma"},"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":"2411.15439","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-23T03:46:45Z","cross_cats_sorted":[],"title_canon_sha256":"d163d26e646f51158a130c65af22163e8c1a20baa34462c5b67019ea6e4e2dde","abstract_canon_sha256":"8dfe5c876e7fa3c2643a8311e95aaae92a69db26b0f6f6f1fedb6a955b09a04d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:39:34.788522Z","signature_b64":"YygzYG9//xsMBYYPERXTTT/Hc+yXJ+OU667Af7ID70mYOGTTndrdShqghJaoXVUlJ5d00sc+GoVw1bKRbx1XBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53c996c508f90d492f4fe43caf5848a2eaeb8a023185d7f383da2fbf0f285133","last_reissued_at":"2026-07-05T09:39:34.788015Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:39:34.788015Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Twin Trigger Generative Networks for Backdoor Attacks against Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guanggang Geng, Jian Weng, Shreyank N Gowda, Shuyuan Lin, Xiaobo Jin, Zhi Liu, Zhiying Li","submitted_at":"2024-11-23T03:46:45Z","abstract_excerpt":"Object detectors, which are widely used in real-world applications, are vulnerable to backdoor attacks. This vulnerability arises because many users rely on datasets or pre-trained models provided by third parties due to constraints on data and resources. However, most research on backdoor attacks has focused on image classification, with limited investigation into object detection. Furthermore, the triggers for most existing backdoor attacks on object detection are manually generated, requiring prior knowledge and consistent patterns between the training and inference stages. This approach ma"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.15439","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/2411.15439/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":"2411.15439","created_at":"2026-07-05T09:39:34.788080+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.15439v1","created_at":"2026-07-05T09:39:34.788080+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.15439","created_at":"2026-07-05T09:39:34.788080+00:00"},{"alias_kind":"pith_short_12","alias_value":"KPEZNRII7EGU","created_at":"2026-07-05T09:39:34.788080+00:00"},{"alias_kind":"pith_short_16","alias_value":"KPEZNRII7EGUSL2P","created_at":"2026-07-05T09:39:34.788080+00:00"},{"alias_kind":"pith_short_8","alias_value":"KPEZNRII","created_at":"2026-07-05T09:39:34.788080+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.07504","citing_title":"Backdoor Attacks and Defenses in Computer Vision Domain: A Survey","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KPEZNRII7EGUSL2P4Q6K6WCIUL","json":"https://pith.science/pith/KPEZNRII7EGUSL2P4Q6K6WCIUL.json","graph_json":"https://pith.science/api/pith-number/KPEZNRII7EGUSL2P4Q6K6WCIUL/graph.json","events_json":"https://pith.science/api/pith-number/KPEZNRII7EGUSL2P4Q6K6WCIUL/events.json","paper":"https://pith.science/paper/KPEZNRII"},"agent_actions":{"view_html":"https://pith.science/pith/KPEZNRII7EGUSL2P4Q6K6WCIUL","download_json":"https://pith.science/pith/KPEZNRII7EGUSL2P4Q6K6WCIUL.json","view_paper":"https://pith.science/paper/KPEZNRII","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.15439&json=true","fetch_graph":"https://pith.science/api/pith-number/KPEZNRII7EGUSL2P4Q6K6WCIUL/graph.json","fetch_events":"https://pith.science/api/pith-number/KPEZNRII7EGUSL2P4Q6K6WCIUL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KPEZNRII7EGUSL2P4Q6K6WCIUL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KPEZNRII7EGUSL2P4Q6K6WCIUL/action/storage_attestation","attest_author":"https://pith.science/pith/KPEZNRII7EGUSL2P4Q6K6WCIUL/action/author_attestation","sign_citation":"https://pith.science/pith/KPEZNRII7EGUSL2P4Q6K6WCIUL/action/citation_signature","submit_replication":"https://pith.science/pith/KPEZNRII7EGUSL2P4Q6K6WCIUL/action/replication_record"}},"created_at":"2026-07-05T09:39:34.788080+00:00","updated_at":"2026-07-05T09:39:34.788080+00:00"}