{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VXQRQM5U5ZN5CAVFS5CHRPU62H","short_pith_number":"pith:VXQRQM5U","schema_version":"1.0","canonical_sha256":"ade11833b4ee5bd102a5974478be9ed1e0e5416946d9906d0b5fe51c5641ef47","source":{"kind":"arxiv","id":"2410.24006","version":2},"attestation_state":"computed","paper":{"title":"DiffPAD: Denoising Diffusion-based Adversarial Patch Decontamination","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Anders Holst, Fatemeh Rahimian, Jia Fu, Sepideh Pashami, Xiao Zhang","submitted_at":"2024-10-31T15:09:36Z","abstract_excerpt":"In the ever-evolving adversarial machine learning landscape, developing effective defenses against patch attacks has become a critical challenge, necessitating reliable solutions to safeguard real-world AI systems. Although diffusion models have shown remarkable capacity in image synthesis and have been recently utilized to counter $\\ell_p$-norm bounded attacks, their potential in mitigating localized patch attacks remains largely underexplored. In this work, we propose DiffPAD, a novel framework that harnesses the power of diffusion models for adversarial patch decontamination. DiffPAD first "},"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":"2410.24006","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-31T15:09:36Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4ef69896e957ac017b46b1523f78cfa1ec556ed24783c2ad2d6477bee6752b23","abstract_canon_sha256":"2213d855e3c514a3e7c36fe89f04804a9f5655ee936f1c24a5ceb621ff9f2d56"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:35:14.057765Z","signature_b64":"o7f+LdoDW77ZlZggA1g6jYQYRrVeA2AnvjvutsYhgtrH1S3PBmyRjBnYHQBJ5g8YfJeGsvbtJWis4ATbnQMzBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ade11833b4ee5bd102a5974478be9ed1e0e5416946d9906d0b5fe51c5641ef47","last_reissued_at":"2026-07-05T09:35:14.057227Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:35:14.057227Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DiffPAD: Denoising Diffusion-based Adversarial Patch Decontamination","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Anders Holst, Fatemeh Rahimian, Jia Fu, Sepideh Pashami, Xiao Zhang","submitted_at":"2024-10-31T15:09:36Z","abstract_excerpt":"In the ever-evolving adversarial machine learning landscape, developing effective defenses against patch attacks has become a critical challenge, necessitating reliable solutions to safeguard real-world AI systems. Although diffusion models have shown remarkable capacity in image synthesis and have been recently utilized to counter $\\ell_p$-norm bounded attacks, their potential in mitigating localized patch attacks remains largely underexplored. In this work, we propose DiffPAD, a novel framework that harnesses the power of diffusion models for adversarial patch decontamination. DiffPAD first "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.24006","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/2410.24006/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":"2410.24006","created_at":"2026-07-05T09:35:14.057281+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.24006v2","created_at":"2026-07-05T09:35:14.057281+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.24006","created_at":"2026-07-05T09:35:14.057281+00:00"},{"alias_kind":"pith_short_12","alias_value":"VXQRQM5U5ZN5","created_at":"2026-07-05T09:35:14.057281+00:00"},{"alias_kind":"pith_short_16","alias_value":"VXQRQM5U5ZN5CAVF","created_at":"2026-07-05T09:35:14.057281+00:00"},{"alias_kind":"pith_short_8","alias_value":"VXQRQM5U","created_at":"2026-07-05T09:35:14.057281+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.06856","citing_title":"IAP: Invisible Adversarial Patch Attack through Perceptibility-Aware Localization and Perturbation Optimization","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VXQRQM5U5ZN5CAVFS5CHRPU62H","json":"https://pith.science/pith/VXQRQM5U5ZN5CAVFS5CHRPU62H.json","graph_json":"https://pith.science/api/pith-number/VXQRQM5U5ZN5CAVFS5CHRPU62H/graph.json","events_json":"https://pith.science/api/pith-number/VXQRQM5U5ZN5CAVFS5CHRPU62H/events.json","paper":"https://pith.science/paper/VXQRQM5U"},"agent_actions":{"view_html":"https://pith.science/pith/VXQRQM5U5ZN5CAVFS5CHRPU62H","download_json":"https://pith.science/pith/VXQRQM5U5ZN5CAVFS5CHRPU62H.json","view_paper":"https://pith.science/paper/VXQRQM5U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.24006&json=true","fetch_graph":"https://pith.science/api/pith-number/VXQRQM5U5ZN5CAVFS5CHRPU62H/graph.json","fetch_events":"https://pith.science/api/pith-number/VXQRQM5U5ZN5CAVFS5CHRPU62H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VXQRQM5U5ZN5CAVFS5CHRPU62H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VXQRQM5U5ZN5CAVFS5CHRPU62H/action/storage_attestation","attest_author":"https://pith.science/pith/VXQRQM5U5ZN5CAVFS5CHRPU62H/action/author_attestation","sign_citation":"https://pith.science/pith/VXQRQM5U5ZN5CAVFS5CHRPU62H/action/citation_signature","submit_replication":"https://pith.science/pith/VXQRQM5U5ZN5CAVFS5CHRPU62H/action/replication_record"}},"created_at":"2026-07-05T09:35:14.057281+00:00","updated_at":"2026-07-05T09:35:14.057281+00:00"}