{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:ZM3MAJY5HHWE7TM7BTOJIEEAFV","short_pith_number":"pith:ZM3MAJY5","schema_version":"1.0","canonical_sha256":"cb36c0271d39ec4fcd9f0cdc9410802d690201ede7b80aba3e97c1ad03890826","source":{"kind":"arxiv","id":"1902.10899","version":4},"attestation_state":"computed","paper":{"title":"Adversarial Attack and Defense on Point Sets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Bingbing Ni, Jiancheng Yang, Jinxian Liu, Qiang Zhang, Qi Tian, Rongyao Fang","submitted_at":"2019-02-28T05:27:40Z","abstract_excerpt":"Emergence of the utility of 3D point cloud data in safety-critical vision tasks (e.g., ADAS) urges researchers to pay more attention to the robustness of 3D representations and deep networks. To this end, we develop an attack and defense scheme, dedicated to 3D point cloud data, for preventing 3D point clouds from manipulated as well as pursuing noise-tolerable 3D representation. A set of novel 3D point cloud attack operations are proposed via pointwise gradient perturbation and adversarial point attachment / detachment. We then develop a flexible perturbation-measurement scheme for 3D point c"},"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":"1902.10899","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2019-02-28T05:27:40Z","cross_cats_sorted":["cs.AI","cs.CR","cs.LG"],"title_canon_sha256":"7ff58a820115dea4b9ad948948eb0e95c2cf33be05baa186f7d99f91096454d0","abstract_canon_sha256":"3ac38d675804ceae98a6d127f3f979a6e6c9dc342aa5417f426c4d644d7b9b59"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:44:30.745082Z","signature_b64":"pd8fV8PHPSVK8fDL202WXc5MuxYwhES8NQ+jC9EyBQx35tCnWuW9df+zb19IA++fJaKpap/q0wmWdqh5wZMGCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cb36c0271d39ec4fcd9f0cdc9410802d690201ede7b80aba3e97c1ad03890826","last_reissued_at":"2026-07-05T02:44:30.744591Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:44:30.744591Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adversarial Attack and Defense on Point Sets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Bingbing Ni, Jiancheng Yang, Jinxian Liu, Qiang Zhang, Qi Tian, Rongyao Fang","submitted_at":"2019-02-28T05:27:40Z","abstract_excerpt":"Emergence of the utility of 3D point cloud data in safety-critical vision tasks (e.g., ADAS) urges researchers to pay more attention to the robustness of 3D representations and deep networks. To this end, we develop an attack and defense scheme, dedicated to 3D point cloud data, for preventing 3D point clouds from manipulated as well as pursuing noise-tolerable 3D representation. A set of novel 3D point cloud attack operations are proposed via pointwise gradient perturbation and adversarial point attachment / detachment. We then develop a flexible perturbation-measurement scheme for 3D point c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.10899","kind":"arxiv","version":4},"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/1902.10899/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":"1902.10899","created_at":"2026-07-05T02:44:30.744648+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.10899v4","created_at":"2026-07-05T02:44:30.744648+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.10899","created_at":"2026-07-05T02:44:30.744648+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZM3MAJY5HHWE","created_at":"2026-07-05T02:44:30.744648+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZM3MAJY5HHWE7TM7","created_at":"2026-07-05T02:44:30.744648+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZM3MAJY5","created_at":"2026-07-05T02:44:30.744648+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06484","citing_title":"Assessing the Operational Impact of Poisoning Attacks over Augmented 3D Point Cloud Public Datasets for Connected and Autonomous Vehicles","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2606.29963","citing_title":"Explainability-Aware Frustum Attack: Exposing Structural Vulnerabilities in LiDAR-Based 3D Object Detectors","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29963","citing_title":"Explainability-Aware Frustum Attack: Exposing Structural Vulnerabilities in LiDAR-Based 3D Object Detectors","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07590","citing_title":"Beyond Defenses: Manifold-Aligned Regularization for Intrinsic 3D Point Cloud Robustness","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2412.00404","citing_title":"Hard-Label Black-Box Attacks on 3D Point Clouds","ref_index":100,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07590","citing_title":"Beyond Defenses: Manifold-Aligned Regularization for Intrinsic 3D Point Cloud Robustness","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZM3MAJY5HHWE7TM7BTOJIEEAFV","json":"https://pith.science/pith/ZM3MAJY5HHWE7TM7BTOJIEEAFV.json","graph_json":"https://pith.science/api/pith-number/ZM3MAJY5HHWE7TM7BTOJIEEAFV/graph.json","events_json":"https://pith.science/api/pith-number/ZM3MAJY5HHWE7TM7BTOJIEEAFV/events.json","paper":"https://pith.science/paper/ZM3MAJY5"},"agent_actions":{"view_html":"https://pith.science/pith/ZM3MAJY5HHWE7TM7BTOJIEEAFV","download_json":"https://pith.science/pith/ZM3MAJY5HHWE7TM7BTOJIEEAFV.json","view_paper":"https://pith.science/paper/ZM3MAJY5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.10899&json=true","fetch_graph":"https://pith.science/api/pith-number/ZM3MAJY5HHWE7TM7BTOJIEEAFV/graph.json","fetch_events":"https://pith.science/api/pith-number/ZM3MAJY5HHWE7TM7BTOJIEEAFV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZM3MAJY5HHWE7TM7BTOJIEEAFV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZM3MAJY5HHWE7TM7BTOJIEEAFV/action/storage_attestation","attest_author":"https://pith.science/pith/ZM3MAJY5HHWE7TM7BTOJIEEAFV/action/author_attestation","sign_citation":"https://pith.science/pith/ZM3MAJY5HHWE7TM7BTOJIEEAFV/action/citation_signature","submit_replication":"https://pith.science/pith/ZM3MAJY5HHWE7TM7BTOJIEEAFV/action/replication_record"}},"created_at":"2026-07-05T02:44:30.744648+00:00","updated_at":"2026-07-05T02:44:30.744648+00:00"}