{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EHUCSZHOKK2OUX2IL6O3VOX3HO","short_pith_number":"pith:EHUCSZHO","schema_version":"1.0","canonical_sha256":"21e82964ee52b4ea5f485f9dbabafb3b8c56615bfe1046119e62d8b287646e68","source":{"kind":"arxiv","id":"2408.17064","version":3},"attestation_state":"computed","paper":{"title":"Instant Adversarial Purification with Adversarial Consistency Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Chun Pong Lau, Chun Tong Lei, Hon Ming Yam, Yifei Qian, Zhongliang Guo","submitted_at":"2024-08-30T07:49:35Z","abstract_excerpt":"Neural networks have revolutionized numerous fields with their exceptional performance, yet they remain susceptible to adversarial attacks through subtle perturbations. While diffusion-based purification methods like DiffPure offer promising defense mechanisms, their computational overhead presents a significant practical limitation. In this paper, we introduce One Step Control Purification (OSCP), a novel defense framework that achieves robust adversarial purification in a single Neural Function Evaluation (NFE) within diffusion models. We propose Gaussian Adversarial Noise Distillation (GAND"},"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":"2408.17064","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-30T07:49:35Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"4d786d903504938c775099acc7e4ff975d8ba0e89aae9af49470ecddb37f22d3","abstract_canon_sha256":"864f6956301311fa8b9e55911e9054b79330d73cd2de156d375dd871422924cd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:36:28.015341Z","signature_b64":"tOKIdscUVnknBAE53woQIGNxMDJgrNtpzebkY/M/e1DheAl6Ftfbc1w/NmrHRfIbEFSyGOsjKh/VbVNaej6xDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"21e82964ee52b4ea5f485f9dbabafb3b8c56615bfe1046119e62d8b287646e68","last_reissued_at":"2026-07-05T10:36:28.014820Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:36:28.014820Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Instant Adversarial Purification with Adversarial Consistency Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Chun Pong Lau, Chun Tong Lei, Hon Ming Yam, Yifei Qian, Zhongliang Guo","submitted_at":"2024-08-30T07:49:35Z","abstract_excerpt":"Neural networks have revolutionized numerous fields with their exceptional performance, yet they remain susceptible to adversarial attacks through subtle perturbations. While diffusion-based purification methods like DiffPure offer promising defense mechanisms, their computational overhead presents a significant practical limitation. In this paper, we introduce One Step Control Purification (OSCP), a novel defense framework that achieves robust adversarial purification in a single Neural Function Evaluation (NFE) within diffusion models. We propose Gaussian Adversarial Noise Distillation (GAND"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.17064","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/2408.17064/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":"2408.17064","created_at":"2026-07-05T10:36:28.014879+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.17064v3","created_at":"2026-07-05T10:36:28.014879+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.17064","created_at":"2026-07-05T10:36:28.014879+00:00"},{"alias_kind":"pith_short_12","alias_value":"EHUCSZHOKK2O","created_at":"2026-07-05T10:36:28.014879+00:00"},{"alias_kind":"pith_short_16","alias_value":"EHUCSZHOKK2OUX2I","created_at":"2026-07-05T10:36:28.014879+00:00"},{"alias_kind":"pith_short_8","alias_value":"EHUCSZHO","created_at":"2026-07-05T10:36:28.014879+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2502.05206","citing_title":"Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EHUCSZHOKK2OUX2IL6O3VOX3HO","json":"https://pith.science/pith/EHUCSZHOKK2OUX2IL6O3VOX3HO.json","graph_json":"https://pith.science/api/pith-number/EHUCSZHOKK2OUX2IL6O3VOX3HO/graph.json","events_json":"https://pith.science/api/pith-number/EHUCSZHOKK2OUX2IL6O3VOX3HO/events.json","paper":"https://pith.science/paper/EHUCSZHO"},"agent_actions":{"view_html":"https://pith.science/pith/EHUCSZHOKK2OUX2IL6O3VOX3HO","download_json":"https://pith.science/pith/EHUCSZHOKK2OUX2IL6O3VOX3HO.json","view_paper":"https://pith.science/paper/EHUCSZHO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.17064&json=true","fetch_graph":"https://pith.science/api/pith-number/EHUCSZHOKK2OUX2IL6O3VOX3HO/graph.json","fetch_events":"https://pith.science/api/pith-number/EHUCSZHOKK2OUX2IL6O3VOX3HO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EHUCSZHOKK2OUX2IL6O3VOX3HO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EHUCSZHOKK2OUX2IL6O3VOX3HO/action/storage_attestation","attest_author":"https://pith.science/pith/EHUCSZHOKK2OUX2IL6O3VOX3HO/action/author_attestation","sign_citation":"https://pith.science/pith/EHUCSZHOKK2OUX2IL6O3VOX3HO/action/citation_signature","submit_replication":"https://pith.science/pith/EHUCSZHOKK2OUX2IL6O3VOX3HO/action/replication_record"}},"created_at":"2026-07-05T10:36:28.014879+00:00","updated_at":"2026-07-05T10:36:28.014879+00:00"}