{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:OAB5US5SC7WFJD6JWMLB6GZPLB","short_pith_number":"pith:OAB5US5S","schema_version":"1.0","canonical_sha256":"7003da4bb217ec548fc9b3161f1b2f58467ba8881e6c0797007c110e7d5062d2","source":{"kind":"arxiv","id":"2104.12146","version":3},"attestation_state":"computed","paper":{"title":"3D Adversarial Attacks Beyond Point Cloud","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Binbin Liu, Bo Ouyang, Jihong Zhu, Jinlai Zhang, Lyujie Chen, Qizhi Xie, Weiming Li, Yanmei Meng","submitted_at":"2021-04-25T13:01:41Z","abstract_excerpt":"Recently, 3D deep learning models have been shown to be susceptible to adversarial attacks like their 2D counterparts. Most of the state-of-the-art (SOTA) 3D adversarial attacks perform perturbation to 3D point clouds. To reproduce these attacks in the physical scenario, a generated adversarial 3D point cloud need to be reconstructed to mesh, which leads to a significant drop in its adversarial effect. In this paper, we propose a strong 3D adversarial attack named Mesh Attack to address this problem by directly performing perturbation on mesh of a 3D object. In order to take advantage of the m"},"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":"2104.12146","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-04-25T13:01:41Z","cross_cats_sorted":[],"title_canon_sha256":"12eb2c2862cccc10dafad46ed5218ddac6e1ba50e9a88d77653f84a45619129d","abstract_canon_sha256":"24eaaa6c9686a769234aaec050659ec27f47a29b8af1ddc8a351eb08f24b39e9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:32:01.656208Z","signature_b64":"/o6hAcyVM80o7ilU6qYKP7T142uUXeUluLOGZydEdfQ62CKYEzNrPZwyvCw0gL0slewSp1uaGcEQ3cffUpUJAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7003da4bb217ec548fc9b3161f1b2f58467ba8881e6c0797007c110e7d5062d2","last_reissued_at":"2026-07-05T03:32:01.655729Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:32:01.655729Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"3D Adversarial Attacks Beyond Point Cloud","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Binbin Liu, Bo Ouyang, Jihong Zhu, Jinlai Zhang, Lyujie Chen, Qizhi Xie, Weiming Li, Yanmei Meng","submitted_at":"2021-04-25T13:01:41Z","abstract_excerpt":"Recently, 3D deep learning models have been shown to be susceptible to adversarial attacks like their 2D counterparts. Most of the state-of-the-art (SOTA) 3D adversarial attacks perform perturbation to 3D point clouds. To reproduce these attacks in the physical scenario, a generated adversarial 3D point cloud need to be reconstructed to mesh, which leads to a significant drop in its adversarial effect. In this paper, we propose a strong 3D adversarial attack named Mesh Attack to address this problem by directly performing perturbation on mesh of a 3D object. In order to take advantage of the m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.12146","kind":"arxiv","version":3},"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/2104.12146/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":"2104.12146","created_at":"2026-07-05T03:32:01.655792+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.12146v3","created_at":"2026-07-05T03:32:01.655792+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.12146","created_at":"2026-07-05T03:32:01.655792+00:00"},{"alias_kind":"pith_short_12","alias_value":"OAB5US5SC7WF","created_at":"2026-07-05T03:32:01.655792+00:00"},{"alias_kind":"pith_short_16","alias_value":"OAB5US5SC7WFJD6J","created_at":"2026-07-05T03:32:01.655792+00:00"},{"alias_kind":"pith_short_8","alias_value":"OAB5US5S","created_at":"2026-07-05T03:32:01.655792+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.18457","citing_title":"Revisiting Physically Realizable Adversarial Object Attack against LiDAR-based Detection: Clarifying Problem Formulation and Experimental Protocols","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OAB5US5SC7WFJD6JWMLB6GZPLB","json":"https://pith.science/pith/OAB5US5SC7WFJD6JWMLB6GZPLB.json","graph_json":"https://pith.science/api/pith-number/OAB5US5SC7WFJD6JWMLB6GZPLB/graph.json","events_json":"https://pith.science/api/pith-number/OAB5US5SC7WFJD6JWMLB6GZPLB/events.json","paper":"https://pith.science/paper/OAB5US5S"},"agent_actions":{"view_html":"https://pith.science/pith/OAB5US5SC7WFJD6JWMLB6GZPLB","download_json":"https://pith.science/pith/OAB5US5SC7WFJD6JWMLB6GZPLB.json","view_paper":"https://pith.science/paper/OAB5US5S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.12146&json=true","fetch_graph":"https://pith.science/api/pith-number/OAB5US5SC7WFJD6JWMLB6GZPLB/graph.json","fetch_events":"https://pith.science/api/pith-number/OAB5US5SC7WFJD6JWMLB6GZPLB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OAB5US5SC7WFJD6JWMLB6GZPLB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OAB5US5SC7WFJD6JWMLB6GZPLB/action/storage_attestation","attest_author":"https://pith.science/pith/OAB5US5SC7WFJD6JWMLB6GZPLB/action/author_attestation","sign_citation":"https://pith.science/pith/OAB5US5SC7WFJD6JWMLB6GZPLB/action/citation_signature","submit_replication":"https://pith.science/pith/OAB5US5SC7WFJD6JWMLB6GZPLB/action/replication_record"}},"created_at":"2026-07-05T03:32:01.655792+00:00","updated_at":"2026-07-05T03:32:01.655792+00:00"}