{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:6TCPQXVCT5KSK7VXPSP3J63KCB","short_pith_number":"pith:6TCPQXVC","schema_version":"1.0","canonical_sha256":"f4c4f85ea29f55257eb77c9fb4fb6a10556d181800351330d7a490c36bb1d8e2","source":{"kind":"arxiv","id":"2104.07395","version":2},"attestation_state":"computed","paper":{"title":"Robust Backdoor Attacks against Deep Neural Networks in Real Physical World","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Can He, Jian Wang, Mingfu Xue, Shichang Sun, Weiqiang Liu","submitted_at":"2021-04-15T11:51:14Z","abstract_excerpt":"Deep neural networks (DNN) have been widely deployed in various applications. However, many researches indicated that DNN is vulnerable to backdoor attacks. The attacker can create a hidden backdoor in target DNN model, and trigger the malicious behaviors by submitting specific backdoor instance. However, almost all the existing backdoor works focused on the digital domain, while few studies investigate the backdoor attacks in real physical world. Restricted to a variety of physical constraints, the performance of backdoor attacks in the real physical world will be severely degraded. In this p"},"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":"2104.07395","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2021-04-15T11:51:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7dd52ee6855408a51fa4d3d31dff62d20681a7063f42c96ae53b05179988ba34","abstract_canon_sha256":"2ecf630f47185f6396f5f6e05e94f7eea27b91526b005001d25d1cf3af9e098e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:36:45.817758Z","signature_b64":"YNrz5ijTi7d2ZB9r25lljG/ljyqpJLG4ETqk125yKXu4D0DPva2ysaM2AxL9B3LOT1rCr3GIFHGbhDivE9/WBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f4c4f85ea29f55257eb77c9fb4fb6a10556d181800351330d7a490c36bb1d8e2","last_reissued_at":"2026-07-05T04:36:45.817376Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:36:45.817376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust Backdoor Attacks against Deep Neural Networks in Real Physical World","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Can He, Jian Wang, Mingfu Xue, Shichang Sun, Weiqiang Liu","submitted_at":"2021-04-15T11:51:14Z","abstract_excerpt":"Deep neural networks (DNN) have been widely deployed in various applications. However, many researches indicated that DNN is vulnerable to backdoor attacks. The attacker can create a hidden backdoor in target DNN model, and trigger the malicious behaviors by submitting specific backdoor instance. However, almost all the existing backdoor works focused on the digital domain, while few studies investigate the backdoor attacks in real physical world. Restricted to a variety of physical constraints, the performance of backdoor attacks in the real physical world will be severely degraded. In this p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.07395","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/2104.07395/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":"2104.07395","created_at":"2026-07-05T04:36:45.817433+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.07395v2","created_at":"2026-07-05T04:36:45.817433+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.07395","created_at":"2026-07-05T04:36:45.817433+00:00"},{"alias_kind":"pith_short_12","alias_value":"6TCPQXVCT5KS","created_at":"2026-07-05T04:36:45.817433+00:00"},{"alias_kind":"pith_short_16","alias_value":"6TCPQXVCT5KSK7VX","created_at":"2026-07-05T04:36:45.817433+00:00"},{"alias_kind":"pith_short_8","alias_value":"6TCPQXVC","created_at":"2026-07-05T04:36:45.817433+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.15101","citing_title":"Comprehensive Evaluation of Cloaking Backdoor Attacks on Object Detector in Real-World","ref_index":45,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6TCPQXVCT5KSK7VXPSP3J63KCB","json":"https://pith.science/pith/6TCPQXVCT5KSK7VXPSP3J63KCB.json","graph_json":"https://pith.science/api/pith-number/6TCPQXVCT5KSK7VXPSP3J63KCB/graph.json","events_json":"https://pith.science/api/pith-number/6TCPQXVCT5KSK7VXPSP3J63KCB/events.json","paper":"https://pith.science/paper/6TCPQXVC"},"agent_actions":{"view_html":"https://pith.science/pith/6TCPQXVCT5KSK7VXPSP3J63KCB","download_json":"https://pith.science/pith/6TCPQXVCT5KSK7VXPSP3J63KCB.json","view_paper":"https://pith.science/paper/6TCPQXVC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.07395&json=true","fetch_graph":"https://pith.science/api/pith-number/6TCPQXVCT5KSK7VXPSP3J63KCB/graph.json","fetch_events":"https://pith.science/api/pith-number/6TCPQXVCT5KSK7VXPSP3J63KCB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6TCPQXVCT5KSK7VXPSP3J63KCB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6TCPQXVCT5KSK7VXPSP3J63KCB/action/storage_attestation","attest_author":"https://pith.science/pith/6TCPQXVCT5KSK7VXPSP3J63KCB/action/author_attestation","sign_citation":"https://pith.science/pith/6TCPQXVCT5KSK7VXPSP3J63KCB/action/citation_signature","submit_replication":"https://pith.science/pith/6TCPQXVCT5KSK7VXPSP3J63KCB/action/replication_record"}},"created_at":"2026-07-05T04:36:45.817433+00:00","updated_at":"2026-07-05T04:36:45.817433+00:00"}