{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:JL3WFIAUL4E22NH2VUCG2K477H","short_pith_number":"pith:JL3WFIAU","schema_version":"1.0","canonical_sha256":"4af762a0145f09ad34faad046d2b9ff9f2157ee5891a695f0c523852cf419991","source":{"kind":"arxiv","id":"2106.06041","version":1},"attestation_state":"computed","paper":{"title":"Adversarial purification with Score-based generative models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Jongmin Yoon, Juho Lee, Sung Ju Hwang","submitted_at":"2021-06-11T04:35:36Z","abstract_excerpt":"While adversarial training is considered as a standard defense method against adversarial attacks for image classifiers, adversarial purification, which purifies attacked images into clean images with a standalone purification model, has shown promises as an alternative defense method. Recently, an Energy-Based Model (EBM) trained with Markov-Chain Monte-Carlo (MCMC) has been highlighted as a purification model, where an attacked image is purified by running a long Markov-chain using the gradients of the EBM. Yet, the practicality of the adversarial purification using an EBM remains questionab"},"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":"2106.06041","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-11T04:35:36Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"383c5c172c5dd66620884098ddde36d6e1a08bf6aa9abc7bf925d921714e92b8","abstract_canon_sha256":"49faf335a840c4f86b856a5d0f62d5edcc5b9a11fe7b8de3d3e2e4ef22e591b7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:48:25.390647Z","signature_b64":"VeALII/y2P2il9UD6N89ZZ5rV7o+tzuBPWEwLynwPjS48dM+pYmG5DeM2mCKS7OTtxts8nx214In3IRSJ+icDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4af762a0145f09ad34faad046d2b9ff9f2157ee5891a695f0c523852cf419991","last_reissued_at":"2026-07-05T02:48:25.390101Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:48:25.390101Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adversarial purification with Score-based generative models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Jongmin Yoon, Juho Lee, Sung Ju Hwang","submitted_at":"2021-06-11T04:35:36Z","abstract_excerpt":"While adversarial training is considered as a standard defense method against adversarial attacks for image classifiers, adversarial purification, which purifies attacked images into clean images with a standalone purification model, has shown promises as an alternative defense method. Recently, an Energy-Based Model (EBM) trained with Markov-Chain Monte-Carlo (MCMC) has been highlighted as a purification model, where an attacked image is purified by running a long Markov-chain using the gradients of the EBM. Yet, the practicality of the adversarial purification using an EBM remains questionab"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.06041","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/2106.06041/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":"2106.06041","created_at":"2026-07-05T02:48:25.390159+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.06041v1","created_at":"2026-07-05T02:48:25.390159+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.06041","created_at":"2026-07-05T02:48:25.390159+00:00"},{"alias_kind":"pith_short_12","alias_value":"JL3WFIAUL4E2","created_at":"2026-07-05T02:48:25.390159+00:00"},{"alias_kind":"pith_short_16","alias_value":"JL3WFIAUL4E22NH2","created_at":"2026-07-05T02:48:25.390159+00:00"},{"alias_kind":"pith_short_8","alias_value":"JL3WFIAU","created_at":"2026-07-05T02:48:25.390159+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.06357","citing_title":"Memory Efficient Full-gradient Attacks (MEFA) Framework for Adversarial Defense Evaluations","ref_index":52,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JL3WFIAUL4E22NH2VUCG2K477H","json":"https://pith.science/pith/JL3WFIAUL4E22NH2VUCG2K477H.json","graph_json":"https://pith.science/api/pith-number/JL3WFIAUL4E22NH2VUCG2K477H/graph.json","events_json":"https://pith.science/api/pith-number/JL3WFIAUL4E22NH2VUCG2K477H/events.json","paper":"https://pith.science/paper/JL3WFIAU"},"agent_actions":{"view_html":"https://pith.science/pith/JL3WFIAUL4E22NH2VUCG2K477H","download_json":"https://pith.science/pith/JL3WFIAUL4E22NH2VUCG2K477H.json","view_paper":"https://pith.science/paper/JL3WFIAU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.06041&json=true","fetch_graph":"https://pith.science/api/pith-number/JL3WFIAUL4E22NH2VUCG2K477H/graph.json","fetch_events":"https://pith.science/api/pith-number/JL3WFIAUL4E22NH2VUCG2K477H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JL3WFIAUL4E22NH2VUCG2K477H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JL3WFIAUL4E22NH2VUCG2K477H/action/storage_attestation","attest_author":"https://pith.science/pith/JL3WFIAUL4E22NH2VUCG2K477H/action/author_attestation","sign_citation":"https://pith.science/pith/JL3WFIAUL4E22NH2VUCG2K477H/action/citation_signature","submit_replication":"https://pith.science/pith/JL3WFIAUL4E22NH2VUCG2K477H/action/replication_record"}},"created_at":"2026-07-05T02:48:25.390159+00:00","updated_at":"2026-07-05T02:48:25.390159+00:00"}