{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RYOQBQZMGVDAVFYYZGLZHXFQB5","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":"e0f2c1f10376b9a20a611752ac10f86d3932157ad7b4b3eef09209a0ad62d356","cross_cats_sorted":["cs.CL","cs.CR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-31T17:07:15Z","title_canon_sha256":"b63df225b51d4ac137d477efd0bb3bec26554399c14c489bb0ce880c465eb9ac"},"schema_version":"1.0","source":{"id":"2405.21018","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.21018","created_at":"2026-07-05T08:27:49Z"},{"alias_kind":"arxiv_version","alias_value":"2405.21018v2","created_at":"2026-07-05T08:27:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.21018","created_at":"2026-07-05T08:27:49Z"},{"alias_kind":"pith_short_12","alias_value":"RYOQBQZMGVDA","created_at":"2026-07-05T08:27:49Z"},{"alias_kind":"pith_short_16","alias_value":"RYOQBQZMGVDAVFYY","created_at":"2026-07-05T08:27:49Z"},{"alias_kind":"pith_short_8","alias_value":"RYOQBQZM","created_at":"2026-07-05T08:27:49Z"}],"graph_snapshots":[{"event_id":"sha256:a31fc746a660965daac7f782e46414d0fd0d18916230cb78e28f3a17770821e8","target":"graph","created_at":"2026-07-05T08:27:49Z","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/2405.21018/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) are being rapidly developed, and a key component of their widespread deployment is their safety-related alignment. Many red-teaming efforts aim to jailbreak LLMs, where among these efforts, the Greedy Coordinate Gradient (GCG) attack's success has led to a growing interest in the study of optimization-based jailbreaking techniques. Although GCG is a significant milestone, its attacking efficiency remains unsatisfactory. In this paper, we present several improved (empirical) techniques for optimization-based jailbreaks like GCG. We first observe that the single targ","authors_text":"Chao Du, Jindong Gu, Min Lin, Tianyu Pang, Xiaochun Cao, Xiaojun Jia, Yang Liu, Yihao Huang","cross_cats":["cs.CL","cs.CR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-31T17:07:15Z","title":"Improved Techniques for Optimization-Based Jailbreaking on Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.21018","kind":"arxiv","version":2},"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:dbab590b013df95ffc2498243a58e712842daf3af91f61825e796a121a85b07b","target":"record","created_at":"2026-07-05T08:27:49Z","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":"e0f2c1f10376b9a20a611752ac10f86d3932157ad7b4b3eef09209a0ad62d356","cross_cats_sorted":["cs.CL","cs.CR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-31T17:07:15Z","title_canon_sha256":"b63df225b51d4ac137d477efd0bb3bec26554399c14c489bb0ce880c465eb9ac"},"schema_version":"1.0","source":{"id":"2405.21018","kind":"arxiv","version":2}},"canonical_sha256":"8e1d00c32c35460a9718c99793dcb00f740757ed74455b3b91a29c05f72bedec","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8e1d00c32c35460a9718c99793dcb00f740757ed74455b3b91a29c05f72bedec","first_computed_at":"2026-07-05T08:27:49.441697Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:27:49.441697Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sZzkl8Ctd7tEuflR/etPsWaVYjRkY/bNVPhX4PNsuRB5aQqyDWQytkXfkmTqIy6b0zgF6FgrN1PGrCdzP7XZAg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:27:49.442204Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.21018","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dbab590b013df95ffc2498243a58e712842daf3af91f61825e796a121a85b07b","sha256:a31fc746a660965daac7f782e46414d0fd0d18916230cb78e28f3a17770821e8"],"state_sha256":"088b06d990dabcf0bf6771376e76e15b95389a725e20ee30fd65cbff4d7faed2"}