{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RACEEXFFMSYGDPI4M2LFVMPUU2","short_pith_number":"pith:RACEEXFF","schema_version":"1.0","canonical_sha256":"8804425ca564b061bd1c66965ab1f4a6b395438fa4cdb4992b9f82fe64106cd9","source":{"kind":"arxiv","id":"2605.18907","version":1},"attestation_state":"computed","paper":{"title":"Lightweight and Fast Backdoor Model Detection","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Chunwei Tian, Daoqiang Zhang, Jiajia Liu, Jing Fang, Qi Zhu, Xuewen Zhang, Yinbo Yu","submitted_at":"2026-05-17T16:02:40Z","abstract_excerpt":"Deep neural networks (DNN), despite their remarkable performance, are highly vulnerable to backdoor attacks. Existing defenses mainly rely on activation anomaly analysis or trigger reverse engineering and often require clean samples or prior knowledge of trigger patterns, resulting in limited efficacy, practicability, and generalizability. More critically, while advanced attacks can implement backdoor implantation in milliseconds, current detection approaches typically demand minutes or even hours. To this end, we propose DFBScanner, a lightweight static parameter inspection framework for fast"},"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":"2605.18907","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CR","submitted_at":"2026-05-17T16:02:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5368ed99728800236c2148cf4144c22f11af2257811b309f2867bf0fd2a1a5da","abstract_canon_sha256":"c913f4b87a2ad24b8b626994b51650c53745fee9a0afb31103570e1879b44550"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:06:31.491954Z","signature_b64":"yCcYyoZ98foLqWW7Sivkbmc6zwuYMLl54AJDebl5cgxf9YJqunuWydkQgZjN2Yf+Ny271uXWTlD9Bqnb3d5rAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8804425ca564b061bd1c66965ab1f4a6b395438fa4cdb4992b9f82fe64106cd9","last_reissued_at":"2026-05-20T00:06:31.491252Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:06:31.491252Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Lightweight and Fast Backdoor Model Detection","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Chunwei Tian, Daoqiang Zhang, Jiajia Liu, Jing Fang, Qi Zhu, Xuewen Zhang, Yinbo Yu","submitted_at":"2026-05-17T16:02:40Z","abstract_excerpt":"Deep neural networks (DNN), despite their remarkable performance, are highly vulnerable to backdoor attacks. Existing defenses mainly rely on activation anomaly analysis or trigger reverse engineering and often require clean samples or prior knowledge of trigger patterns, resulting in limited efficacy, practicability, and generalizability. More critically, while advanced attacks can implement backdoor implantation in milliseconds, current detection approaches typically demand minutes or even hours. To this end, we propose DFBScanner, a lightweight static parameter inspection framework for fast"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18907","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/2605.18907/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":"2605.18907","created_at":"2026-05-20T00:06:31.491361+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.18907v1","created_at":"2026-05-20T00:06:31.491361+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18907","created_at":"2026-05-20T00:06:31.491361+00:00"},{"alias_kind":"pith_short_12","alias_value":"RACEEXFFMSYG","created_at":"2026-05-20T00:06:31.491361+00:00"},{"alias_kind":"pith_short_16","alias_value":"RACEEXFFMSYGDPI4","created_at":"2026-05-20T00:06:31.491361+00:00"},{"alias_kind":"pith_short_8","alias_value":"RACEEXFF","created_at":"2026-05-20T00:06:31.491361+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/RACEEXFFMSYGDPI4M2LFVMPUU2","json":"https://pith.science/pith/RACEEXFFMSYGDPI4M2LFVMPUU2.json","graph_json":"https://pith.science/api/pith-number/RACEEXFFMSYGDPI4M2LFVMPUU2/graph.json","events_json":"https://pith.science/api/pith-number/RACEEXFFMSYGDPI4M2LFVMPUU2/events.json","paper":"https://pith.science/paper/RACEEXFF"},"agent_actions":{"view_html":"https://pith.science/pith/RACEEXFFMSYGDPI4M2LFVMPUU2","download_json":"https://pith.science/pith/RACEEXFFMSYGDPI4M2LFVMPUU2.json","view_paper":"https://pith.science/paper/RACEEXFF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.18907&json=true","fetch_graph":"https://pith.science/api/pith-number/RACEEXFFMSYGDPI4M2LFVMPUU2/graph.json","fetch_events":"https://pith.science/api/pith-number/RACEEXFFMSYGDPI4M2LFVMPUU2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RACEEXFFMSYGDPI4M2LFVMPUU2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RACEEXFFMSYGDPI4M2LFVMPUU2/action/storage_attestation","attest_author":"https://pith.science/pith/RACEEXFFMSYGDPI4M2LFVMPUU2/action/author_attestation","sign_citation":"https://pith.science/pith/RACEEXFFMSYGDPI4M2LFVMPUU2/action/citation_signature","submit_replication":"https://pith.science/pith/RACEEXFFMSYGDPI4M2LFVMPUU2/action/replication_record"}},"created_at":"2026-05-20T00:06:31.491361+00:00","updated_at":"2026-05-20T00:06:31.491361+00:00"}