{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:67YERUMPFHQHXP63OGIKMZ35PW","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":"1bcb9f5ab1bbfeec31fd6eaffb0237c73a8c5703ae099c3d4e7137324b7a6e7c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2024-08-20T20:35:04Z","title_canon_sha256":"1d63f1effa3a0f6015790e599d770cb9a5695543f1bf1a6e779d354c590c8c5d"},"schema_version":"1.0","source":{"id":"2408.11182","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.11182","created_at":"2026-07-05T10:10:43Z"},{"alias_kind":"arxiv_version","alias_value":"2408.11182v2","created_at":"2026-07-05T10:10:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.11182","created_at":"2026-07-05T10:10:43Z"},{"alias_kind":"pith_short_12","alias_value":"67YERUMPFHQH","created_at":"2026-07-05T10:10:43Z"},{"alias_kind":"pith_short_16","alias_value":"67YERUMPFHQHXP63","created_at":"2026-07-05T10:10:43Z"},{"alias_kind":"pith_short_8","alias_value":"67YERUMP","created_at":"2026-07-05T10:10:43Z"}],"graph_snapshots":[{"event_id":"sha256:45d730f29688a555592bd8c595fbc4f388a8587068b14b337f23bed91a3f932a","target":"graph","created_at":"2026-07-05T10:10:43Z","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/2408.11182/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Model (LLM) jailbreak refers to a type of attack aimed to bypass the safeguard of an LLM to generate contents that are inconsistent with the safe usage guidelines. Based on the insights from the self-attention computation process, this paper proposes a novel blackbox jailbreak approach, which involves crafting the payload prompt by strategically injecting the prohibited query into a carrier article. The carrier article maintains the semantic proximity to the prohibited query, which is automatically produced by combining a hypernymy article and a context, both of which are genera","authors_text":"Haizhou Wang, Lan Zhang, Nanqing Luo, Peng Liu, Xiaoyan Sun, Yebo Cao, Zhilong Wang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2024-08-20T20:35:04Z","title":"Hide Your Malicious Goal Into Benign Narratives: Jailbreak Large Language Models through Carrier Articles"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.11182","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:e558dd232fa6297a956ca421ed8dce0b3e3652f15aff02a92cb9d0fcc9cc255e","target":"record","created_at":"2026-07-05T10:10:43Z","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":"1bcb9f5ab1bbfeec31fd6eaffb0237c73a8c5703ae099c3d4e7137324b7a6e7c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2024-08-20T20:35:04Z","title_canon_sha256":"1d63f1effa3a0f6015790e599d770cb9a5695543f1bf1a6e779d354c590c8c5d"},"schema_version":"1.0","source":{"id":"2408.11182","kind":"arxiv","version":2}},"canonical_sha256":"f7f048d18f29e07bbfdb7190a6677d7db39299e789dcb5d2b2e522cab1558ef4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f7f048d18f29e07bbfdb7190a6677d7db39299e789dcb5d2b2e522cab1558ef4","first_computed_at":"2026-07-05T10:10:43.302800Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:10:43.302800Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"a4OIGGlSIXpGTEMgowfYKdnMqywF+TytE7aqs2IMXMLY3SsmEB4hfs/bROUqON2JPlB3F6jj37jHn248IM9IBA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:10:43.303280Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.11182","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e558dd232fa6297a956ca421ed8dce0b3e3652f15aff02a92cb9d0fcc9cc255e","sha256:45d730f29688a555592bd8c595fbc4f388a8587068b14b337f23bed91a3f932a"],"state_sha256":"d7a740e6b45d5534b022bff387cd710ed9fe85168479e6fafc65113c002cb66f"}