{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TE2DRPVW6WQAZF3LRGJ45H2JFZ","short_pith_number":"pith:TE2DRPVW","schema_version":"1.0","canonical_sha256":"993438beb6f5a00c976b8993ce9f492e4ec961690965a0a4a65b428f2a99d2e2","source":{"kind":"arxiv","id":"2402.14968","version":3},"attestation_state":"computed","paper":{"title":"Mitigating Fine-tuning based Jailbreak Attack with Backdoor Enhanced Safety Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CR","authors_text":"Bo Li, Chaowei Xiao, Jiazhao Li, Jiongxiao Wang, Junjie Hu, Muhao Chen, Patrick McDaniel, Xiangyu Qi, Yiquan Li, Yixuan Li","submitted_at":"2024-02-22T21:05:18Z","abstract_excerpt":"Despite the general capabilities of Large Language Models (LLM), these models still request fine-tuning or adaptation with customized data when meeting specific business demands. However, this process inevitably introduces new threats, particularly against the Fine-tuning based Jailbreak Attack (FJAttack) under the setting of Language-Model-as-a-Service (LMaaS), where the model's safety has been significantly compromised by fine-tuning users' uploaded examples contain just a few harmful examples. Though potential defenses have been proposed that the service providers can integrate safety examp"},"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":"2402.14968","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2024-02-22T21:05:18Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"500807f470bec68ea3f868dafcdd2dc39d8d68e5d565fcc1a95fee31597061bf","abstract_canon_sha256":"2e4ec0c0b4ba4f64e40221fcf09e84f9b3775f9faa47ebd1e873245ef60a6ea5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:34:13.887704Z","signature_b64":"fzvFq9/1+EfRGeCGgLpnKFSHFNkOMJWdlvq4JmBLDzfmyX3/sn1wij+lywBI6dE8uKgPnzddbQCYrmeBHJecDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"993438beb6f5a00c976b8993ce9f492e4ec961690965a0a4a65b428f2a99d2e2","last_reissued_at":"2026-07-05T08:34:13.887172Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:34:13.887172Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mitigating Fine-tuning based Jailbreak Attack with Backdoor Enhanced Safety Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CR","authors_text":"Bo Li, Chaowei Xiao, Jiazhao Li, Jiongxiao Wang, Junjie Hu, Muhao Chen, Patrick McDaniel, Xiangyu Qi, Yiquan Li, Yixuan Li","submitted_at":"2024-02-22T21:05:18Z","abstract_excerpt":"Despite the general capabilities of Large Language Models (LLM), these models still request fine-tuning or adaptation with customized data when meeting specific business demands. However, this process inevitably introduces new threats, particularly against the Fine-tuning based Jailbreak Attack (FJAttack) under the setting of Language-Model-as-a-Service (LMaaS), where the model's safety has been significantly compromised by fine-tuning users' uploaded examples contain just a few harmful examples. Though potential defenses have been proposed that the service providers can integrate safety examp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.14968","kind":"arxiv","version":3},"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/2402.14968/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":"2402.14968","created_at":"2026-07-05T08:34:13.887245+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.14968v3","created_at":"2026-07-05T08:34:13.887245+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.14968","created_at":"2026-07-05T08:34:13.887245+00:00"},{"alias_kind":"pith_short_12","alias_value":"TE2DRPVW6WQA","created_at":"2026-07-05T08:34:13.887245+00:00"},{"alias_kind":"pith_short_16","alias_value":"TE2DRPVW6WQAZF3L","created_at":"2026-07-05T08:34:13.887245+00:00"},{"alias_kind":"pith_short_8","alias_value":"TE2DRPVW","created_at":"2026-07-05T08:34:13.887245+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2409.18169","citing_title":"Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey","ref_index":157,"is_internal_anchor":false},{"citing_arxiv_id":"2407.04295","citing_title":"Jailbreak Attacks and Defenses Against Large Language Models: A Survey","ref_index":94,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TE2DRPVW6WQAZF3LRGJ45H2JFZ","json":"https://pith.science/pith/TE2DRPVW6WQAZF3LRGJ45H2JFZ.json","graph_json":"https://pith.science/api/pith-number/TE2DRPVW6WQAZF3LRGJ45H2JFZ/graph.json","events_json":"https://pith.science/api/pith-number/TE2DRPVW6WQAZF3LRGJ45H2JFZ/events.json","paper":"https://pith.science/paper/TE2DRPVW"},"agent_actions":{"view_html":"https://pith.science/pith/TE2DRPVW6WQAZF3LRGJ45H2JFZ","download_json":"https://pith.science/pith/TE2DRPVW6WQAZF3LRGJ45H2JFZ.json","view_paper":"https://pith.science/paper/TE2DRPVW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.14968&json=true","fetch_graph":"https://pith.science/api/pith-number/TE2DRPVW6WQAZF3LRGJ45H2JFZ/graph.json","fetch_events":"https://pith.science/api/pith-number/TE2DRPVW6WQAZF3LRGJ45H2JFZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TE2DRPVW6WQAZF3LRGJ45H2JFZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TE2DRPVW6WQAZF3LRGJ45H2JFZ/action/storage_attestation","attest_author":"https://pith.science/pith/TE2DRPVW6WQAZF3LRGJ45H2JFZ/action/author_attestation","sign_citation":"https://pith.science/pith/TE2DRPVW6WQAZF3LRGJ45H2JFZ/action/citation_signature","submit_replication":"https://pith.science/pith/TE2DRPVW6WQAZF3LRGJ45H2JFZ/action/replication_record"}},"created_at":"2026-07-05T08:34:13.887245+00:00","updated_at":"2026-07-05T08:34:13.887245+00:00"}