{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:A5IIVGLZMS4O2VG2N6OKTAQXZP","short_pith_number":"pith:A5IIVGLZ","schema_version":"1.0","canonical_sha256":"07508a997964b8ed54da6f9ca98217cbf61940590fb9c41e3c6a2bf3894203bb","source":{"kind":"arxiv","id":"2104.11101","version":1},"attestation_state":"computed","paper":{"title":"Learning Transferable 3D Adversarial Cloaks for Deep Trained Detectors","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Arman Maesumi, Chandrajit Bajaj, Mingkang Zhu, Tianlong Chen, Yi Wang, Zhangyang Wang","submitted_at":"2021-04-22T14:36:08Z","abstract_excerpt":"This paper presents a novel patch-based adversarial attack pipeline that trains adversarial patches on 3D human meshes. We sample triangular faces on a reference human mesh, and create an adversarial texture atlas over those faces. The adversarial texture is transferred to human meshes in various poses, which are rendered onto a collection of real-world background images. Contrary to the traditional patch-based adversarial attacks, where prior work attempts to fool trained object detectors using appended adversarial patches, this new form of attack is mapped into the 3D object world and back-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":"2104.11101","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-04-22T14:36:08Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b541efe1a277f965bea668956748540c37a4b298e2ead1ad320c9df028add761","abstract_canon_sha256":"1329b6921df96f31f96cd446fa3a627e96b94ef60b7207cf72bbc0997f73fde3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:34:17.658989Z","signature_b64":"Pf95I2Ff+uhpRUlXjvQqkj1qVulGGvCGqC+PePhqaCRxHdE0HgvWJCcQw4smNO8hhWGdIlDv3nf92s1J+LHYBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"07508a997964b8ed54da6f9ca98217cbf61940590fb9c41e3c6a2bf3894203bb","last_reissued_at":"2026-07-05T02:34:17.658561Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:34:17.658561Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Transferable 3D Adversarial Cloaks for Deep Trained Detectors","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Arman Maesumi, Chandrajit Bajaj, Mingkang Zhu, Tianlong Chen, Yi Wang, Zhangyang Wang","submitted_at":"2021-04-22T14:36:08Z","abstract_excerpt":"This paper presents a novel patch-based adversarial attack pipeline that trains adversarial patches on 3D human meshes. We sample triangular faces on a reference human mesh, and create an adversarial texture atlas over those faces. The adversarial texture is transferred to human meshes in various poses, which are rendered onto a collection of real-world background images. Contrary to the traditional patch-based adversarial attacks, where prior work attempts to fool trained object detectors using appended adversarial patches, this new form of attack is mapped into the 3D object world and back-p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.11101","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/2104.11101/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":"2104.11101","created_at":"2026-07-05T02:34:17.658633+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.11101v1","created_at":"2026-07-05T02:34:17.658633+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.11101","created_at":"2026-07-05T02:34:17.658633+00:00"},{"alias_kind":"pith_short_12","alias_value":"A5IIVGLZMS4O","created_at":"2026-07-05T02:34:17.658633+00:00"},{"alias_kind":"pith_short_16","alias_value":"A5IIVGLZMS4O2VG2","created_at":"2026-07-05T02:34:17.658633+00:00"},{"alias_kind":"pith_short_8","alias_value":"A5IIVGLZ","created_at":"2026-07-05T02:34:17.658633+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.16402","citing_title":"AdvReal: Physical Adversarial Patch Generation Framework for Security Evaluation of Object Detection Systems","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A5IIVGLZMS4O2VG2N6OKTAQXZP","json":"https://pith.science/pith/A5IIVGLZMS4O2VG2N6OKTAQXZP.json","graph_json":"https://pith.science/api/pith-number/A5IIVGLZMS4O2VG2N6OKTAQXZP/graph.json","events_json":"https://pith.science/api/pith-number/A5IIVGLZMS4O2VG2N6OKTAQXZP/events.json","paper":"https://pith.science/paper/A5IIVGLZ"},"agent_actions":{"view_html":"https://pith.science/pith/A5IIVGLZMS4O2VG2N6OKTAQXZP","download_json":"https://pith.science/pith/A5IIVGLZMS4O2VG2N6OKTAQXZP.json","view_paper":"https://pith.science/paper/A5IIVGLZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.11101&json=true","fetch_graph":"https://pith.science/api/pith-number/A5IIVGLZMS4O2VG2N6OKTAQXZP/graph.json","fetch_events":"https://pith.science/api/pith-number/A5IIVGLZMS4O2VG2N6OKTAQXZP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A5IIVGLZMS4O2VG2N6OKTAQXZP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A5IIVGLZMS4O2VG2N6OKTAQXZP/action/storage_attestation","attest_author":"https://pith.science/pith/A5IIVGLZMS4O2VG2N6OKTAQXZP/action/author_attestation","sign_citation":"https://pith.science/pith/A5IIVGLZMS4O2VG2N6OKTAQXZP/action/citation_signature","submit_replication":"https://pith.science/pith/A5IIVGLZMS4O2VG2N6OKTAQXZP/action/replication_record"}},"created_at":"2026-07-05T02:34:17.658633+00:00","updated_at":"2026-07-05T02:34:17.658633+00:00"}