{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CM3SFDNJ2O6HDTHP42G5CSZNYI","short_pith_number":"pith:CM3SFDNJ","schema_version":"1.0","canonical_sha256":"1337228da9d3bc71ccefe68dd14b2dc208d5b8d4669b21800c0f68b583f7c928","source":{"kind":"arxiv","id":"2411.18956","version":1},"attestation_state":"computed","paper":{"title":"Random Sampling for Diffusion-based Adversarial Purification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Jiancheng Zhang, Peiran Dong, Song Guo, Yin-ping Zhao, Yongyong Chen","submitted_at":"2024-11-28T07:04:09Z","abstract_excerpt":"Denoising Diffusion Probabilistic Models (DDPMs) have gained great attention in adversarial purification. Current diffusion-based works focus on designing effective condition-guided mechanisms while ignoring a fundamental problem, i.e., the original DDPM sampling is intended for stable generation, which may not be the optimal solution for adversarial purification. Inspired by the stability of the Denoising Diffusion Implicit Model (DDIM), we propose an opposite sampling scheme called random sampling. In brief, random sampling will sample from a random noisy space during each diffusion process,"},"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":"2411.18956","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-28T07:04:09Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"686ed4e4887adf0be6e51e8ffc631dd81bebeae07bb22294721710106979431b","abstract_canon_sha256":"ba8f75bd01e7560dc1a27b0fad09ef34e4bad17463b506cc573e31fd62d7ed8b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:41:54.617668Z","signature_b64":"prCTfnKqQJOo6oH88RXTmfsScuWQ/XwGm5oc3Qf1hBlsXz6EkjfArWpga1nN8Xo86yazS/0CSLIo9B5+iH4vBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1337228da9d3bc71ccefe68dd14b2dc208d5b8d4669b21800c0f68b583f7c928","last_reissued_at":"2026-07-05T09:41:54.617296Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:41:54.617296Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Random Sampling for Diffusion-based Adversarial Purification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Jiancheng Zhang, Peiran Dong, Song Guo, Yin-ping Zhao, Yongyong Chen","submitted_at":"2024-11-28T07:04:09Z","abstract_excerpt":"Denoising Diffusion Probabilistic Models (DDPMs) have gained great attention in adversarial purification. Current diffusion-based works focus on designing effective condition-guided mechanisms while ignoring a fundamental problem, i.e., the original DDPM sampling is intended for stable generation, which may not be the optimal solution for adversarial purification. Inspired by the stability of the Denoising Diffusion Implicit Model (DDIM), we propose an opposite sampling scheme called random sampling. In brief, random sampling will sample from a random noisy space during each diffusion process,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.18956","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/2411.18956/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":"2411.18956","created_at":"2026-07-05T09:41:54.617368+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.18956v1","created_at":"2026-07-05T09:41:54.617368+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.18956","created_at":"2026-07-05T09:41:54.617368+00:00"},{"alias_kind":"pith_short_12","alias_value":"CM3SFDNJ2O6H","created_at":"2026-07-05T09:41:54.617368+00:00"},{"alias_kind":"pith_short_16","alias_value":"CM3SFDNJ2O6HDTHP","created_at":"2026-07-05T09:41:54.617368+00:00"},{"alias_kind":"pith_short_8","alias_value":"CM3SFDNJ","created_at":"2026-07-05T09:41:54.617368+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CM3SFDNJ2O6HDTHP42G5CSZNYI","json":"https://pith.science/pith/CM3SFDNJ2O6HDTHP42G5CSZNYI.json","graph_json":"https://pith.science/api/pith-number/CM3SFDNJ2O6HDTHP42G5CSZNYI/graph.json","events_json":"https://pith.science/api/pith-number/CM3SFDNJ2O6HDTHP42G5CSZNYI/events.json","paper":"https://pith.science/paper/CM3SFDNJ"},"agent_actions":{"view_html":"https://pith.science/pith/CM3SFDNJ2O6HDTHP42G5CSZNYI","download_json":"https://pith.science/pith/CM3SFDNJ2O6HDTHP42G5CSZNYI.json","view_paper":"https://pith.science/paper/CM3SFDNJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.18956&json=true","fetch_graph":"https://pith.science/api/pith-number/CM3SFDNJ2O6HDTHP42G5CSZNYI/graph.json","fetch_events":"https://pith.science/api/pith-number/CM3SFDNJ2O6HDTHP42G5CSZNYI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CM3SFDNJ2O6HDTHP42G5CSZNYI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CM3SFDNJ2O6HDTHP42G5CSZNYI/action/storage_attestation","attest_author":"https://pith.science/pith/CM3SFDNJ2O6HDTHP42G5CSZNYI/action/author_attestation","sign_citation":"https://pith.science/pith/CM3SFDNJ2O6HDTHP42G5CSZNYI/action/citation_signature","submit_replication":"https://pith.science/pith/CM3SFDNJ2O6HDTHP42G5CSZNYI/action/replication_record"}},"created_at":"2026-07-05T09:41:54.617368+00:00","updated_at":"2026-07-05T09:41:54.617368+00:00"}