{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XMMEOWMJ7T7X6HZDAQUBRVCVHJ","short_pith_number":"pith:XMMEOWMJ","schema_version":"1.0","canonical_sha256":"bb18475989fcff7f1f23042818d4553a6d58541622ea946a9913f0824ff7c61f","source":{"kind":"arxiv","id":"2408.04839","version":1},"attestation_state":"computed","paper":{"title":"Adversarially Robust Industrial Anomaly Detection Through Diffusion Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Jinghui Chen, Lu Lin, Yuanpu Cao","submitted_at":"2024-08-09T03:25:19Z","abstract_excerpt":"Deep learning-based industrial anomaly detection models have achieved remarkably high accuracy on commonly used benchmark datasets. However, the robustness of those models may not be satisfactory due to the existence of adversarial examples, which pose significant threats to the practical deployment of deep anomaly detectors. Recently, it has been shown that diffusion models can be used to purify the adversarial noises and thus build a robust classifier against adversarial attacks. Unfortunately, we found that naively applying this strategy in anomaly detection (i.e., placing a purifier before"},"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":"2408.04839","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-09T03:25:19Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"2cb6a7282d8bba1f1aec3e71370c9a35ec3ddc9d729e3ec7470d1ce2839d7153","abstract_canon_sha256":"83ad5112f285858595cca41d406b1ad7537efd21d54241948b1e933135958137"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:53:44.837870Z","signature_b64":"NCh+2YW6g6ob9e9tfBCpYCm6LnFj4LoFWWvQesnSYiWRjqftry11mrV110RgJ6ZaWmo2ppb9F2ajhqA9zg/UBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb18475989fcff7f1f23042818d4553a6d58541622ea946a9913f0824ff7c61f","last_reissued_at":"2026-07-05T08:53:44.837394Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:53:44.837394Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adversarially Robust Industrial Anomaly Detection Through Diffusion Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Jinghui Chen, Lu Lin, Yuanpu Cao","submitted_at":"2024-08-09T03:25:19Z","abstract_excerpt":"Deep learning-based industrial anomaly detection models have achieved remarkably high accuracy on commonly used benchmark datasets. However, the robustness of those models may not be satisfactory due to the existence of adversarial examples, which pose significant threats to the practical deployment of deep anomaly detectors. Recently, it has been shown that diffusion models can be used to purify the adversarial noises and thus build a robust classifier against adversarial attacks. Unfortunately, we found that naively applying this strategy in anomaly detection (i.e., placing a purifier before"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.04839","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/2408.04839/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":"2408.04839","created_at":"2026-07-05T08:53:44.837456+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.04839v1","created_at":"2026-07-05T08:53:44.837456+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.04839","created_at":"2026-07-05T08:53:44.837456+00:00"},{"alias_kind":"pith_short_12","alias_value":"XMMEOWMJ7T7X","created_at":"2026-07-05T08:53:44.837456+00:00"},{"alias_kind":"pith_short_16","alias_value":"XMMEOWMJ7T7X6HZD","created_at":"2026-07-05T08:53:44.837456+00:00"},{"alias_kind":"pith_short_8","alias_value":"XMMEOWMJ","created_at":"2026-07-05T08:53:44.837456+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.07690","citing_title":"Fortifying Time Series: DTW-Certified Robust Anomaly Detection","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XMMEOWMJ7T7X6HZDAQUBRVCVHJ","json":"https://pith.science/pith/XMMEOWMJ7T7X6HZDAQUBRVCVHJ.json","graph_json":"https://pith.science/api/pith-number/XMMEOWMJ7T7X6HZDAQUBRVCVHJ/graph.json","events_json":"https://pith.science/api/pith-number/XMMEOWMJ7T7X6HZDAQUBRVCVHJ/events.json","paper":"https://pith.science/paper/XMMEOWMJ"},"agent_actions":{"view_html":"https://pith.science/pith/XMMEOWMJ7T7X6HZDAQUBRVCVHJ","download_json":"https://pith.science/pith/XMMEOWMJ7T7X6HZDAQUBRVCVHJ.json","view_paper":"https://pith.science/paper/XMMEOWMJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.04839&json=true","fetch_graph":"https://pith.science/api/pith-number/XMMEOWMJ7T7X6HZDAQUBRVCVHJ/graph.json","fetch_events":"https://pith.science/api/pith-number/XMMEOWMJ7T7X6HZDAQUBRVCVHJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XMMEOWMJ7T7X6HZDAQUBRVCVHJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XMMEOWMJ7T7X6HZDAQUBRVCVHJ/action/storage_attestation","attest_author":"https://pith.science/pith/XMMEOWMJ7T7X6HZDAQUBRVCVHJ/action/author_attestation","sign_citation":"https://pith.science/pith/XMMEOWMJ7T7X6HZDAQUBRVCVHJ/action/citation_signature","submit_replication":"https://pith.science/pith/XMMEOWMJ7T7X6HZDAQUBRVCVHJ/action/replication_record"}},"created_at":"2026-07-05T08:53:44.837456+00:00","updated_at":"2026-07-05T08:53:44.837456+00:00"}