{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZX4ZA4QLXX5D2FDK2HITLLJRFY","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"79230b68b3034da342dff89d54e2b51a9d0d8e56927e5cb0730b4d3f404860a1","cross_cats_sorted":["cs.CR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-25T13:38:40Z","title_canon_sha256":"89ea185486146241766b8ab0f2809b4b1f6a3484dbd548b48d56808d8faace15"},"schema_version":"1.0","source":{"id":"2405.16229","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.16229","created_at":"2026-07-05T08:23:27Z"},{"alias_kind":"arxiv_version","alias_value":"2405.16229v1","created_at":"2026-07-05T08:23:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.16229","created_at":"2026-07-05T08:23:27Z"},{"alias_kind":"pith_short_12","alias_value":"ZX4ZA4QLXX5D","created_at":"2026-07-05T08:23:27Z"},{"alias_kind":"pith_short_16","alias_value":"ZX4ZA4QLXX5D2FDK","created_at":"2026-07-05T08:23:27Z"},{"alias_kind":"pith_short_8","alias_value":"ZX4ZA4QL","created_at":"2026-07-05T08:23:27Z"}],"graph_snapshots":[{"event_id":"sha256:742992a1146ec0868a4116c097b893b3f8b429c6f973869f955eb2ecd61edcf6","target":"graph","created_at":"2026-07-05T08:23:27Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2405.16229/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The existing safety alignment of Large Language Models (LLMs) is found fragile and could be easily attacked through different strategies, such as through fine-tuning on a few harmful examples or manipulating the prefix of the generation results. However, the attack mechanisms of these strategies are still underexplored. In this paper, we ask the following question: \\textit{while these approaches can all significantly compromise safety, do their attack mechanisms exhibit strong similarities?} To answer this question, we break down the safeguarding process of an LLM when encountered with harmful","authors_text":"Chak Tou Leong, Hanlin Wang, Jian Wang, Kaishuai Xu, Wenjie Li, Yi Cheng","cross_cats":["cs.CR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-25T13:38:40Z","title":"No Two Devils Alike: Unveiling Distinct Mechanisms of Fine-tuning Attacks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.16229","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:00e06aedf38dec601b67899b27ea6801f2ae122a8ea26d9cb8a75a1e91dbfc3f","target":"record","created_at":"2026-07-05T08:23:27Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"79230b68b3034da342dff89d54e2b51a9d0d8e56927e5cb0730b4d3f404860a1","cross_cats_sorted":["cs.CR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-25T13:38:40Z","title_canon_sha256":"89ea185486146241766b8ab0f2809b4b1f6a3484dbd548b48d56808d8faace15"},"schema_version":"1.0","source":{"id":"2405.16229","kind":"arxiv","version":1}},"canonical_sha256":"cdf990720bbdfa3d146ad1d135ad312e2d9512a86ac67367d5da7957d4f3d46e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cdf990720bbdfa3d146ad1d135ad312e2d9512a86ac67367d5da7957d4f3d46e","first_computed_at":"2026-07-05T08:23:27.511043Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:23:27.511043Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fDVn4v6hd793dxTMrwfQa9ybFEOWToYnREquh4/VDAGkvsybvVe5gp4Kn8Ra5yzhDnjg0Df9HoEl7DFR60D3CA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:23:27.511618Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.16229","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:00e06aedf38dec601b67899b27ea6801f2ae122a8ea26d9cb8a75a1e91dbfc3f","sha256:742992a1146ec0868a4116c097b893b3f8b429c6f973869f955eb2ecd61edcf6"],"state_sha256":"e27527dc7f436d66cd34726a0e2fccda5fe260acb46bbd2208c4f5cb86bbbbbf"}