{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ROQU5RNEOYFGB56PSI5NVTNS2G","short_pith_number":"pith:ROQU5RNE","schema_version":"1.0","canonical_sha256":"8ba14ec5a4760a60f7cf923adacdb2d18c6ee94449700e18fb9b11b41d8a5203","source":{"kind":"arxiv","id":"2408.15861","version":1},"attestation_state":"computed","paper":{"title":"Fusing Pruned and Backdoored Models: Optimal Transport-based Data-free Backdoor Mitigation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"Hui Xiong, Jianze Li, Li Liu, Weilin Lin","submitted_at":"2024-08-28T15:21:10Z","abstract_excerpt":"Backdoor attacks present a serious security threat to deep neuron networks (DNNs). Although numerous effective defense techniques have been proposed in recent years, they inevitably rely on the availability of either clean or poisoned data. In contrast, data-free defense techniques have evolved slowly and still lag significantly in performance. To address this issue, different from the traditional approach of pruning followed by fine-tuning, we propose a novel data-free defense method named Optimal Transport-based Backdoor Repairing (OTBR) in this work. This method, based on our findings on ne"},"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":"2408.15861","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-08-28T15:21:10Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"27429211afd87f0e3924c18a92b0eba9e6af27c6967b9b6275be914d068a7f16","abstract_canon_sha256":"661b2ee6752f03a8f52acbcbb6825972bdce0cf268656b7ab83b1979df480e79"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:00:18.640401Z","signature_b64":"vXkB0dol3Cz+9h8/00goxjOJ1KK0dzwxlktO4jSFsG32XFiDngyBs7t9YHgdhD5Bk6zAvfMgq9bbKskg6r0UBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ba14ec5a4760a60f7cf923adacdb2d18c6ee94449700e18fb9b11b41d8a5203","last_reissued_at":"2026-07-05T09:00:18.639933Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:00:18.639933Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fusing Pruned and Backdoored Models: Optimal Transport-based Data-free Backdoor Mitigation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"Hui Xiong, Jianze Li, Li Liu, Weilin Lin","submitted_at":"2024-08-28T15:21:10Z","abstract_excerpt":"Backdoor attacks present a serious security threat to deep neuron networks (DNNs). Although numerous effective defense techniques have been proposed in recent years, they inevitably rely on the availability of either clean or poisoned data. In contrast, data-free defense techniques have evolved slowly and still lag significantly in performance. To address this issue, different from the traditional approach of pruning followed by fine-tuning, we propose a novel data-free defense method named Optimal Transport-based Backdoor Repairing (OTBR) in this work. This method, based on our findings on ne"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.15861","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/2408.15861/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":"2408.15861","created_at":"2026-07-05T09:00:18.639989+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.15861v1","created_at":"2026-07-05T09:00:18.639989+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.15861","created_at":"2026-07-05T09:00:18.639989+00:00"},{"alias_kind":"pith_short_12","alias_value":"ROQU5RNEOYFG","created_at":"2026-07-05T09:00:18.639989+00:00"},{"alias_kind":"pith_short_16","alias_value":"ROQU5RNEOYFGB56P","created_at":"2026-07-05T09:00:18.639989+00:00"},{"alias_kind":"pith_short_8","alias_value":"ROQU5RNE","created_at":"2026-07-05T09:00:18.639989+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.07231","citing_title":"Revisiting the Auxiliary Data in Backdoor Purification","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ROQU5RNEOYFGB56PSI5NVTNS2G","json":"https://pith.science/pith/ROQU5RNEOYFGB56PSI5NVTNS2G.json","graph_json":"https://pith.science/api/pith-number/ROQU5RNEOYFGB56PSI5NVTNS2G/graph.json","events_json":"https://pith.science/api/pith-number/ROQU5RNEOYFGB56PSI5NVTNS2G/events.json","paper":"https://pith.science/paper/ROQU5RNE"},"agent_actions":{"view_html":"https://pith.science/pith/ROQU5RNEOYFGB56PSI5NVTNS2G","download_json":"https://pith.science/pith/ROQU5RNEOYFGB56PSI5NVTNS2G.json","view_paper":"https://pith.science/paper/ROQU5RNE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.15861&json=true","fetch_graph":"https://pith.science/api/pith-number/ROQU5RNEOYFGB56PSI5NVTNS2G/graph.json","fetch_events":"https://pith.science/api/pith-number/ROQU5RNEOYFGB56PSI5NVTNS2G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ROQU5RNEOYFGB56PSI5NVTNS2G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ROQU5RNEOYFGB56PSI5NVTNS2G/action/storage_attestation","attest_author":"https://pith.science/pith/ROQU5RNEOYFGB56PSI5NVTNS2G/action/author_attestation","sign_citation":"https://pith.science/pith/ROQU5RNEOYFGB56PSI5NVTNS2G/action/citation_signature","submit_replication":"https://pith.science/pith/ROQU5RNEOYFGB56PSI5NVTNS2G/action/replication_record"}},"created_at":"2026-07-05T09:00:18.639989+00:00","updated_at":"2026-07-05T09:00:18.639989+00:00"}