{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ZD7UYIUNV3P25N5PZKLQDM5WJC","short_pith_number":"pith:ZD7UYIUN","schema_version":"1.0","canonical_sha256":"c8ff4c228daedfaeb7afca9701b3b648a4e4fbc804a1660fc9166d3d308f65ab","source":{"kind":"arxiv","id":"2305.15241","version":2},"attestation_state":"computed","paper":{"title":"Robust Classification via a Single Diffusion Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Chengqi Duan, Hang Su, Huanran Chen, Jun Zhu, Xiao Yang, Yinpeng Dong, Zhengyi Wang","submitted_at":"2023-05-24T15:25:19Z","abstract_excerpt":"Diffusion models have been applied to improve adversarial robustness of image classifiers by purifying the adversarial noises or generating realistic data for adversarial training. However, diffusion-based purification can be evaded by stronger adaptive attacks while adversarial training does not perform well under unseen threats, exhibiting inevitable limitations of these methods. To better harness the expressive power of diffusion models, this paper proposes Robust Diffusion Classifier (RDC), a generative classifier that is constructed from a pre-trained diffusion model to be adversarially r"},"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":"2305.15241","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-24T15:25:19Z","cross_cats_sorted":["cs.CR","cs.LG"],"title_canon_sha256":"e1621995603229190a6aac0d407d539a3a82c2fb5ece2ca54efe2e98c2ffe55b","abstract_canon_sha256":"a6a3a64e1ed2617985533ff4c326c53dd6bd10a4c06ef57f40208b4e5942a2e2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:21:05.044408Z","signature_b64":"7VS39qu6R+2ZHXCrVPdA33oswthXZ7ocfuL8hnrZIGy7YZVs5mA3Ec4Z9koqGvWbWrKZsX70BgvXcZeIEQSOCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c8ff4c228daedfaeb7afca9701b3b648a4e4fbc804a1660fc9166d3d308f65ab","last_reissued_at":"2026-07-05T08:21:05.043891Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:21:05.043891Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust Classification via a Single Diffusion Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Chengqi Duan, Hang Su, Huanran Chen, Jun Zhu, Xiao Yang, Yinpeng Dong, Zhengyi Wang","submitted_at":"2023-05-24T15:25:19Z","abstract_excerpt":"Diffusion models have been applied to improve adversarial robustness of image classifiers by purifying the adversarial noises or generating realistic data for adversarial training. However, diffusion-based purification can be evaded by stronger adaptive attacks while adversarial training does not perform well under unseen threats, exhibiting inevitable limitations of these methods. To better harness the expressive power of diffusion models, this paper proposes Robust Diffusion Classifier (RDC), a generative classifier that is constructed from a pre-trained diffusion model to be adversarially r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.15241","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2305.15241/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":"2305.15241","created_at":"2026-07-05T08:21:05.043951+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.15241v2","created_at":"2026-07-05T08:21:05.043951+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.15241","created_at":"2026-07-05T08:21:05.043951+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZD7UYIUNV3P2","created_at":"2026-07-05T08:21:05.043951+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZD7UYIUNV3P25N5P","created_at":"2026-07-05T08:21:05.043951+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZD7UYIUN","created_at":"2026-07-05T08:21:05.043951+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.02284","citing_title":"FlowCIR: Semantic Transport via Flow Matching for Zero-Shot Composed Image Retrieval","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07599","citing_title":"DiffoR: A Unified Continuous Generative Framework for Universal Ordinal Regression","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06357","citing_title":"Memory Efficient Full-gradient Attacks (MEFA) Framework for Adversarial Defense Evaluations","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZD7UYIUNV3P25N5PZKLQDM5WJC","json":"https://pith.science/pith/ZD7UYIUNV3P25N5PZKLQDM5WJC.json","graph_json":"https://pith.science/api/pith-number/ZD7UYIUNV3P25N5PZKLQDM5WJC/graph.json","events_json":"https://pith.science/api/pith-number/ZD7UYIUNV3P25N5PZKLQDM5WJC/events.json","paper":"https://pith.science/paper/ZD7UYIUN"},"agent_actions":{"view_html":"https://pith.science/pith/ZD7UYIUNV3P25N5PZKLQDM5WJC","download_json":"https://pith.science/pith/ZD7UYIUNV3P25N5PZKLQDM5WJC.json","view_paper":"https://pith.science/paper/ZD7UYIUN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.15241&json=true","fetch_graph":"https://pith.science/api/pith-number/ZD7UYIUNV3P25N5PZKLQDM5WJC/graph.json","fetch_events":"https://pith.science/api/pith-number/ZD7UYIUNV3P25N5PZKLQDM5WJC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZD7UYIUNV3P25N5PZKLQDM5WJC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZD7UYIUNV3P25N5PZKLQDM5WJC/action/storage_attestation","attest_author":"https://pith.science/pith/ZD7UYIUNV3P25N5PZKLQDM5WJC/action/author_attestation","sign_citation":"https://pith.science/pith/ZD7UYIUNV3P25N5PZKLQDM5WJC/action/citation_signature","submit_replication":"https://pith.science/pith/ZD7UYIUNV3P25N5PZKLQDM5WJC/action/replication_record"}},"created_at":"2026-07-05T08:21:05.043951+00:00","updated_at":"2026-07-05T08:21:05.043951+00:00"}