{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WWLXMIXMJICHTDPLEGHLM6DDEJ","short_pith_number":"pith:WWLXMIXM","schema_version":"1.0","canonical_sha256":"b5977622ec4a04798deb218eb678632260fe966fd670c8ddf8d82e673eb6b2cf","source":{"kind":"arxiv","id":"2505.14531","version":1},"attestation_state":"computed","paper":{"title":"SifterNet: A Generalized and Model-Agnostic Trigger Purification Approach","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chi Lin, Mengfan Li, Quanliang Jing, Shaoye Luo, Xinxin Fan, Yongjun Xu, Yunfeng Lu","submitted_at":"2025-05-20T15:51:17Z","abstract_excerpt":"Aiming at resisting backdoor attacks in convolution neural networks and vision Transformer-based large model, this paper proposes a generalized and model-agnostic trigger-purification approach resorting to the classic Ising model. To date, existing trigger detection/removal studies usually require to know the detailed knowledge of target model in advance, access to a large number of clean samples or even model-retraining authorization, which brings the huge inconvenience for practical applications, especially inaccessible to target model. An ideal countermeasure ought to eliminate the implante"},"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":"2505.14531","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-20T15:51:17Z","cross_cats_sorted":[],"title_canon_sha256":"a3d0bc79d55e81f5e38d6eb47c7573d02fb7815bf63460623067e8fe82f7b69a","abstract_canon_sha256":"f4a4b1c41107137eb03d2b75585fa01fd13680bd720fc7cefa3f8e3887922758"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:06:15.064367Z","signature_b64":"7TbJqspwoGdohdp87EP0UQesblgxApxGueeU29PL3N6oFGAesOF6UPqJIaVPHtyh1Njcg32dxb+poTa84q0cCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b5977622ec4a04798deb218eb678632260fe966fd670c8ddf8d82e673eb6b2cf","last_reissued_at":"2026-07-05T11:06:15.063831Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:06:15.063831Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SifterNet: A Generalized and Model-Agnostic Trigger Purification Approach","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chi Lin, Mengfan Li, Quanliang Jing, Shaoye Luo, Xinxin Fan, Yongjun Xu, Yunfeng Lu","submitted_at":"2025-05-20T15:51:17Z","abstract_excerpt":"Aiming at resisting backdoor attacks in convolution neural networks and vision Transformer-based large model, this paper proposes a generalized and model-agnostic trigger-purification approach resorting to the classic Ising model. To date, existing trigger detection/removal studies usually require to know the detailed knowledge of target model in advance, access to a large number of clean samples or even model-retraining authorization, which brings the huge inconvenience for practical applications, especially inaccessible to target model. An ideal countermeasure ought to eliminate the implante"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.14531","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/2505.14531/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":"2505.14531","created_at":"2026-07-05T11:06:15.063897+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.14531v1","created_at":"2026-07-05T11:06:15.063897+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.14531","created_at":"2026-07-05T11:06:15.063897+00:00"},{"alias_kind":"pith_short_12","alias_value":"WWLXMIXMJICH","created_at":"2026-07-05T11:06:15.063897+00:00"},{"alias_kind":"pith_short_16","alias_value":"WWLXMIXMJICHTDPL","created_at":"2026-07-05T11:06:15.063897+00:00"},{"alias_kind":"pith_short_8","alias_value":"WWLXMIXM","created_at":"2026-07-05T11:06:15.063897+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/WWLXMIXMJICHTDPLEGHLM6DDEJ","json":"https://pith.science/pith/WWLXMIXMJICHTDPLEGHLM6DDEJ.json","graph_json":"https://pith.science/api/pith-number/WWLXMIXMJICHTDPLEGHLM6DDEJ/graph.json","events_json":"https://pith.science/api/pith-number/WWLXMIXMJICHTDPLEGHLM6DDEJ/events.json","paper":"https://pith.science/paper/WWLXMIXM"},"agent_actions":{"view_html":"https://pith.science/pith/WWLXMIXMJICHTDPLEGHLM6DDEJ","download_json":"https://pith.science/pith/WWLXMIXMJICHTDPLEGHLM6DDEJ.json","view_paper":"https://pith.science/paper/WWLXMIXM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.14531&json=true","fetch_graph":"https://pith.science/api/pith-number/WWLXMIXMJICHTDPLEGHLM6DDEJ/graph.json","fetch_events":"https://pith.science/api/pith-number/WWLXMIXMJICHTDPLEGHLM6DDEJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WWLXMIXMJICHTDPLEGHLM6DDEJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WWLXMIXMJICHTDPLEGHLM6DDEJ/action/storage_attestation","attest_author":"https://pith.science/pith/WWLXMIXMJICHTDPLEGHLM6DDEJ/action/author_attestation","sign_citation":"https://pith.science/pith/WWLXMIXMJICHTDPLEGHLM6DDEJ/action/citation_signature","submit_replication":"https://pith.science/pith/WWLXMIXMJICHTDPLEGHLM6DDEJ/action/replication_record"}},"created_at":"2026-07-05T11:06:15.063897+00:00","updated_at":"2026-07-05T11:06:15.063897+00:00"}