{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:CFWYI3ELRT2ILXSKLQMMHDYHMH","short_pith_number":"pith:CFWYI3EL","schema_version":"1.0","canonical_sha256":"116d846c8b8cf485de4a5c18c38f0761f8de988786082b64bae87957dc08b67f","source":{"kind":"arxiv","id":"1812.11017","version":2},"attestation_state":"computed","paper":{"title":"DUP-Net: Denoiser and Upsampler Network for 3D Adversarial Point Clouds Defense","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Han Fang, Hang Zhou, Kejiang Chen, Nenghai Yu, Weiming Zhang, Wenbo Zhou","submitted_at":"2018-12-25T00:38:20Z","abstract_excerpt":"Neural networks are vulnerable to adversarial examples, which poses a threat to their application in security sensitive systems. We propose a Denoiser and UPsampler Network (DUP-Net) structure as defenses for 3D adversarial point cloud classification, where the two modules reconstruct surface smoothness by dropping or adding points. In this paper, statistical outlier removal (SOR) and a data-driven upsampling network are considered as denoiser and upsampler respectively. Compared with baseline defenses, DUP-Net has three advantages. First, with DUP-Net as a defense, the target model is more ro"},"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":"1812.11017","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-12-25T00:38:20Z","cross_cats_sorted":[],"title_canon_sha256":"1c25dc9b726673ecdd748b2ce960d2c7ce7fc13d40fe996b299f170c7a14ac38","abstract_canon_sha256":"b060c65a092e99eaea57a280cdaa459f0d32eacc07cc87a218549ef2e70ee07a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:25.163650Z","signature_b64":"2gbZruPBlxuKMyBhxwbYxiezk4Y3/3HymsT+19F+7J1FjqsjBQ6UkZHky8u3z3fhWq6LYcA/++JOBBgaAvWAAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"116d846c8b8cf485de4a5c18c38f0761f8de988786082b64bae87957dc08b67f","last_reissued_at":"2026-05-17T23:39:25.163006Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:25.163006Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DUP-Net: Denoiser and Upsampler Network for 3D Adversarial Point Clouds Defense","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Han Fang, Hang Zhou, Kejiang Chen, Nenghai Yu, Weiming Zhang, Wenbo Zhou","submitted_at":"2018-12-25T00:38:20Z","abstract_excerpt":"Neural networks are vulnerable to adversarial examples, which poses a threat to their application in security sensitive systems. We propose a Denoiser and UPsampler Network (DUP-Net) structure as defenses for 3D adversarial point cloud classification, where the two modules reconstruct surface smoothness by dropping or adding points. In this paper, statistical outlier removal (SOR) and a data-driven upsampling network are considered as denoiser and upsampler respectively. Compared with baseline defenses, DUP-Net has three advantages. First, with DUP-Net as a defense, the target model is more ro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.11017","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":""},"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":"1812.11017","created_at":"2026-05-17T23:39:25.163110+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.11017v2","created_at":"2026-05-17T23:39:25.163110+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.11017","created_at":"2026-05-17T23:39:25.163110+00:00"},{"alias_kind":"pith_short_12","alias_value":"CFWYI3ELRT2I","created_at":"2026-05-18T12:32:16.446611+00:00"},{"alias_kind":"pith_short_16","alias_value":"CFWYI3ELRT2ILXSK","created_at":"2026-05-18T12:32:16.446611+00:00"},{"alias_kind":"pith_short_8","alias_value":"CFWYI3EL","created_at":"2026-05-18T12:32:16.446611+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.07590","citing_title":"Beyond Defenses: Manifold-Aligned Regularization for Intrinsic 3D Point Cloud Robustness","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CFWYI3ELRT2ILXSKLQMMHDYHMH","json":"https://pith.science/pith/CFWYI3ELRT2ILXSKLQMMHDYHMH.json","graph_json":"https://pith.science/api/pith-number/CFWYI3ELRT2ILXSKLQMMHDYHMH/graph.json","events_json":"https://pith.science/api/pith-number/CFWYI3ELRT2ILXSKLQMMHDYHMH/events.json","paper":"https://pith.science/paper/CFWYI3EL"},"agent_actions":{"view_html":"https://pith.science/pith/CFWYI3ELRT2ILXSKLQMMHDYHMH","download_json":"https://pith.science/pith/CFWYI3ELRT2ILXSKLQMMHDYHMH.json","view_paper":"https://pith.science/paper/CFWYI3EL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.11017&json=true","fetch_graph":"https://pith.science/api/pith-number/CFWYI3ELRT2ILXSKLQMMHDYHMH/graph.json","fetch_events":"https://pith.science/api/pith-number/CFWYI3ELRT2ILXSKLQMMHDYHMH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CFWYI3ELRT2ILXSKLQMMHDYHMH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CFWYI3ELRT2ILXSKLQMMHDYHMH/action/storage_attestation","attest_author":"https://pith.science/pith/CFWYI3ELRT2ILXSKLQMMHDYHMH/action/author_attestation","sign_citation":"https://pith.science/pith/CFWYI3ELRT2ILXSKLQMMHDYHMH/action/citation_signature","submit_replication":"https://pith.science/pith/CFWYI3ELRT2ILXSKLQMMHDYHMH/action/replication_record"}},"created_at":"2026-05-17T23:39:25.163110+00:00","updated_at":"2026-05-17T23:39:25.163110+00:00"}