{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:6FB6JOMRJY3DL2KWXEGUA2CQ6V","short_pith_number":"pith:6FB6JOMR","schema_version":"1.0","canonical_sha256":"f143e4b9914e3635e956b90d406850f578e6f262801af1ecf9bd1de04509520c","source":{"kind":"arxiv","id":"2307.15539","version":4},"attestation_state":"computed","paper":{"title":"Beating Backdoor Attack at Its Own Game","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR","cs.CV"],"primary_cat":"cs.LG","authors_text":"Alberto Sangiovanni-Vincentelli, Min Liu, Xiangyu Yue","submitted_at":"2023-07-28T13:07:42Z","abstract_excerpt":"Deep neural networks (DNNs) are vulnerable to backdoor attack, which does not affect the network's performance on clean data but would manipulate the network behavior once a trigger pattern is added. Existing defense methods have greatly reduced attack success rate, but their prediction accuracy on clean data still lags behind a clean model by a large margin. Inspired by the stealthiness and effectiveness of backdoor attack, we propose a simple but highly effective defense framework which injects non-adversarial backdoors targeting poisoned samples. Following the general steps in backdoor atta"},"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":"2307.15539","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-07-28T13:07:42Z","cross_cats_sorted":["cs.CR","cs.CV"],"title_canon_sha256":"8b3982735a18a9c23ff55497ee17f3f830f8ebd5f4333192d827b421a890b4e9","abstract_canon_sha256":"70524fb7c22370d3a10794ac3e18aa3414d0d769ef14e24b5bb23ef5e3e365fa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:44:36.164629Z","signature_b64":"HinlWXP3fImD7AqmqgyETVUW0InzNgpuIRAJOz8F976vJpAz5IFh7J7ur2fgPuwVWLHcuBjvJ9NXgZw7nJNKCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f143e4b9914e3635e956b90d406850f578e6f262801af1ecf9bd1de04509520c","last_reissued_at":"2026-07-05T10:44:36.164158Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:44:36.164158Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beating Backdoor Attack at Its Own Game","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR","cs.CV"],"primary_cat":"cs.LG","authors_text":"Alberto Sangiovanni-Vincentelli, Min Liu, Xiangyu Yue","submitted_at":"2023-07-28T13:07:42Z","abstract_excerpt":"Deep neural networks (DNNs) are vulnerable to backdoor attack, which does not affect the network's performance on clean data but would manipulate the network behavior once a trigger pattern is added. Existing defense methods have greatly reduced attack success rate, but their prediction accuracy on clean data still lags behind a clean model by a large margin. Inspired by the stealthiness and effectiveness of backdoor attack, we propose a simple but highly effective defense framework which injects non-adversarial backdoors targeting poisoned samples. Following the general steps in backdoor atta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.15539","kind":"arxiv","version":4},"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/2307.15539/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":"2307.15539","created_at":"2026-07-05T10:44:36.164212+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.15539v4","created_at":"2026-07-05T10:44:36.164212+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.15539","created_at":"2026-07-05T10:44:36.164212+00:00"},{"alias_kind":"pith_short_12","alias_value":"6FB6JOMRJY3D","created_at":"2026-07-05T10:44:36.164212+00:00"},{"alias_kind":"pith_short_16","alias_value":"6FB6JOMRJY3DL2KW","created_at":"2026-07-05T10:44:36.164212+00:00"},{"alias_kind":"pith_short_8","alias_value":"6FB6JOMR","created_at":"2026-07-05T10:44:36.164212+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/6FB6JOMRJY3DL2KWXEGUA2CQ6V","json":"https://pith.science/pith/6FB6JOMRJY3DL2KWXEGUA2CQ6V.json","graph_json":"https://pith.science/api/pith-number/6FB6JOMRJY3DL2KWXEGUA2CQ6V/graph.json","events_json":"https://pith.science/api/pith-number/6FB6JOMRJY3DL2KWXEGUA2CQ6V/events.json","paper":"https://pith.science/paper/6FB6JOMR"},"agent_actions":{"view_html":"https://pith.science/pith/6FB6JOMRJY3DL2KWXEGUA2CQ6V","download_json":"https://pith.science/pith/6FB6JOMRJY3DL2KWXEGUA2CQ6V.json","view_paper":"https://pith.science/paper/6FB6JOMR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.15539&json=true","fetch_graph":"https://pith.science/api/pith-number/6FB6JOMRJY3DL2KWXEGUA2CQ6V/graph.json","fetch_events":"https://pith.science/api/pith-number/6FB6JOMRJY3DL2KWXEGUA2CQ6V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6FB6JOMRJY3DL2KWXEGUA2CQ6V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6FB6JOMRJY3DL2KWXEGUA2CQ6V/action/storage_attestation","attest_author":"https://pith.science/pith/6FB6JOMRJY3DL2KWXEGUA2CQ6V/action/author_attestation","sign_citation":"https://pith.science/pith/6FB6JOMRJY3DL2KWXEGUA2CQ6V/action/citation_signature","submit_replication":"https://pith.science/pith/6FB6JOMRJY3DL2KWXEGUA2CQ6V/action/replication_record"}},"created_at":"2026-07-05T10:44:36.164212+00:00","updated_at":"2026-07-05T10:44:36.164212+00:00"}