{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CSDIHOFM2RS5GHLC2SIZ3HU7UE","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":"42f245081569588a8e221fa4e03a9e17708e85157a6c87310058a92800879a6c","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2024-07-03T07:14:05Z","title_canon_sha256":"aedbe6f5bb600e4005f85c59ce6dbc2a3cdea15036e47e59ab9ded69b85288a2"},"schema_version":"1.0","source":{"id":"2407.02855","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.02855","created_at":"2026-07-05T11:05:33Z"},{"alias_kind":"arxiv_version","alias_value":"2407.02855v3","created_at":"2026-07-05T11:05:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.02855","created_at":"2026-07-05T11:05:33Z"},{"alias_kind":"pith_short_12","alias_value":"CSDIHOFM2RS5","created_at":"2026-07-05T11:05:33Z"},{"alias_kind":"pith_short_16","alias_value":"CSDIHOFM2RS5GHLC","created_at":"2026-07-05T11:05:33Z"},{"alias_kind":"pith_short_8","alias_value":"CSDIHOFM","created_at":"2026-07-05T11:05:33Z"}],"graph_snapshots":[{"event_id":"sha256:70993737120e9fce8ae7a3599262a8b1e6c353600ad6109bd4fa64667d2e7230","target":"graph","created_at":"2026-07-05T11:05:33Z","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/2407.02855/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) are known to be vulnerable to jailbreak attacks. An important observation is that, while different types of jailbreak attacks can generate significantly different queries, they mostly result in similar responses that are rooted in the same harmful knowledge (e.g., detailed steps to make a bomb). Consequently, unlearning-based approaches have been proposed to mitigate jailbreak attacks by directly removing harmful knowledge from the model. In this paper, we identify a novel ripple effect of unlearning, wherein LLMs can implicitly unlearn harmful knowledge that was n","authors_text":"Chujie Zheng, Hongning Wang, Junxiao Yang, Minlie Huang, Pei Ke, Shiyao Cui, Yida Lu, Zhexin Zhang","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2024-07-03T07:14:05Z","title":"From Theft to Bomb-Making: The Ripple Effect of Unlearning in Defending Against Jailbreak Attacks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.02855","kind":"arxiv","version":3},"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":"sha256:3920760eda0aab8bf288e6180d023dc64d05843369456c89a2f3454fbd673dc8","target":"record","created_at":"2026-07-05T11:05:33Z","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":"42f245081569588a8e221fa4e03a9e17708e85157a6c87310058a92800879a6c","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2024-07-03T07:14:05Z","title_canon_sha256":"aedbe6f5bb600e4005f85c59ce6dbc2a3cdea15036e47e59ab9ded69b85288a2"},"schema_version":"1.0","source":{"id":"2407.02855","kind":"arxiv","version":3}},"canonical_sha256":"148683b8acd465d31d62d4919d9e9fa10007b80f7873fa711736964d590a538c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"148683b8acd465d31d62d4919d9e9fa10007b80f7873fa711736964d590a538c","first_computed_at":"2026-07-05T11:05:33.651147Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:05:33.651147Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"j+Z2rylXU3mnnE4brVSZGg7OVJuHZhUVhI0KHOMB9BTD6AQCj5pU0eWHw8FduYvRssLf2VqRZspKy0tmUZlvDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:05:33.651644Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.02855","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3920760eda0aab8bf288e6180d023dc64d05843369456c89a2f3454fbd673dc8","sha256:70993737120e9fce8ae7a3599262a8b1e6c353600ad6109bd4fa64667d2e7230"],"state_sha256":"a3f1d41d1a074c67ec9b59c8dfa0347100cf594fc53cfb43ecc27605c7bcff23"}