{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:M2R4GC7PN7BB5F7MX4NOF2CL42","short_pith_number":"pith:M2R4GC7P","schema_version":"1.0","canonical_sha256":"66a3c30bef6fc21e97ecbf1ae2e84be6969a2680713972671f33ecb9c15f8b1b","source":{"kind":"arxiv","id":"2409.14940","version":1},"attestation_state":"computed","paper":{"title":"Improving Adversarial Robustness for 3D Point Cloud Recognition at Test-Time through Purified Self-Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jinpeng Lin, Tianrui Li, Xulei Yang, Xun Xu","submitted_at":"2024-09-23T11:46:38Z","abstract_excerpt":"Recognizing 3D point cloud plays a pivotal role in many real-world applications. However, deploying 3D point cloud deep learning model is vulnerable to adversarial attacks. Despite many efforts into developing robust model by adversarial training, they may become less effective against emerging attacks. This limitation motivates the development of adversarial purification which employs generative model to mitigate the impact of adversarial attacks. In this work, we highlight the remaining challenges from two perspectives. First, the purification based method requires retraining the classifier "},"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":"2409.14940","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-23T11:46:38Z","cross_cats_sorted":[],"title_canon_sha256":"658bf9e4c1a93111faad7b0d2b1a382961183591d19efb7118c1e68b4bdb7df5","abstract_canon_sha256":"0ba9d77d2ca5c043f8025c705fee3a88fbe8cbef59e788f1f1094718187986bf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:10:33.664232Z","signature_b64":"XnJw01cXepdszcQSP3BTDc72e0D5WzQX4N+WVHIKHWOxNif71VsRvgQkPbMllHe4DTFxi/6gYf0pfoWT2rcWAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"66a3c30bef6fc21e97ecbf1ae2e84be6969a2680713972671f33ecb9c15f8b1b","last_reissued_at":"2026-07-05T09:10:33.663847Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:10:33.663847Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Adversarial Robustness for 3D Point Cloud Recognition at Test-Time through Purified Self-Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jinpeng Lin, Tianrui Li, Xulei Yang, Xun Xu","submitted_at":"2024-09-23T11:46:38Z","abstract_excerpt":"Recognizing 3D point cloud plays a pivotal role in many real-world applications. However, deploying 3D point cloud deep learning model is vulnerable to adversarial attacks. Despite many efforts into developing robust model by adversarial training, they may become less effective against emerging attacks. This limitation motivates the development of adversarial purification which employs generative model to mitigate the impact of adversarial attacks. In this work, we highlight the remaining challenges from two perspectives. First, the purification based method requires retraining the classifier "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.14940","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/2409.14940/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":"2409.14940","created_at":"2026-07-05T09:10:33.663901+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.14940v1","created_at":"2026-07-05T09:10:33.663901+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.14940","created_at":"2026-07-05T09:10:33.663901+00:00"},{"alias_kind":"pith_short_12","alias_value":"M2R4GC7PN7BB","created_at":"2026-07-05T09:10:33.663901+00:00"},{"alias_kind":"pith_short_16","alias_value":"M2R4GC7PN7BB5F7M","created_at":"2026-07-05T09:10:33.663901+00:00"},{"alias_kind":"pith_short_8","alias_value":"M2R4GC7P","created_at":"2026-07-05T09:10:33.663901+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.22271","citing_title":"Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M2R4GC7PN7BB5F7MX4NOF2CL42","json":"https://pith.science/pith/M2R4GC7PN7BB5F7MX4NOF2CL42.json","graph_json":"https://pith.science/api/pith-number/M2R4GC7PN7BB5F7MX4NOF2CL42/graph.json","events_json":"https://pith.science/api/pith-number/M2R4GC7PN7BB5F7MX4NOF2CL42/events.json","paper":"https://pith.science/paper/M2R4GC7P"},"agent_actions":{"view_html":"https://pith.science/pith/M2R4GC7PN7BB5F7MX4NOF2CL42","download_json":"https://pith.science/pith/M2R4GC7PN7BB5F7MX4NOF2CL42.json","view_paper":"https://pith.science/paper/M2R4GC7P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.14940&json=true","fetch_graph":"https://pith.science/api/pith-number/M2R4GC7PN7BB5F7MX4NOF2CL42/graph.json","fetch_events":"https://pith.science/api/pith-number/M2R4GC7PN7BB5F7MX4NOF2CL42/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M2R4GC7PN7BB5F7MX4NOF2CL42/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M2R4GC7PN7BB5F7MX4NOF2CL42/action/storage_attestation","attest_author":"https://pith.science/pith/M2R4GC7PN7BB5F7MX4NOF2CL42/action/author_attestation","sign_citation":"https://pith.science/pith/M2R4GC7PN7BB5F7MX4NOF2CL42/action/citation_signature","submit_replication":"https://pith.science/pith/M2R4GC7PN7BB5F7MX4NOF2CL42/action/replication_record"}},"created_at":"2026-07-05T09:10:33.663901+00:00","updated_at":"2026-07-05T09:10:33.663901+00:00"}