{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:STC2A4WWIJKS7G6IZCI75AMFJX","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":"695eed76849b1dd3ddbf713e2eee8a0bf5d87d173d5b5d9ceb8e98e931c2f98b","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2024-02-24T05:34:43Z","title_canon_sha256":"492fdfafbaeed0b5b06a47fe9daf92a1cab7b3a0b74f57ecf8edb5cc18189b45"},"schema_version":"1.0","source":{"id":"2402.15727","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.15727","created_at":"2026-07-05T07:51:39Z"},{"alias_kind":"arxiv_version","alias_value":"2402.15727v2","created_at":"2026-07-05T07:51:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.15727","created_at":"2026-07-05T07:51:39Z"},{"alias_kind":"pith_short_12","alias_value":"STC2A4WWIJKS","created_at":"2026-07-05T07:51:39Z"},{"alias_kind":"pith_short_16","alias_value":"STC2A4WWIJKS7G6I","created_at":"2026-07-05T07:51:39Z"},{"alias_kind":"pith_short_8","alias_value":"STC2A4WW","created_at":"2026-07-05T07:51:39Z"}],"graph_snapshots":[{"event_id":"sha256:a534cff4846d9c43139adec18e268bb7614d3cb5185d249e21bd4dc70db674bd","target":"graph","created_at":"2026-07-05T07:51:39Z","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/2402.15727/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Jailbreaking is an emerging adversarial attack that bypasses the safety alignment deployed in off-the-shelf large language models (LLMs). A considerable amount of research exists proposing more effective jailbreak attacks, including the recent Greedy Coordinate Gradient (GCG) attack, jailbreak template-based attacks such as using \"Do-Anything-Now\" (DAN), and multilingual jailbreak. In contrast, the defensive side has been relatively less explored. This paper proposes a lightweight yet practical defense called SELFDEFEND, which can defend against all existing jailbreak attacks with minimal dela","authors_text":"Daoyuan Wu, Ning Liu, Shuai Wang, Yang Liu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2024-02-24T05:34:43Z","title":"LLMs Can Defend Themselves Against Jailbreaking in a Practical Manner: A Vision Paper"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.15727","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":"sha256:7f3f18b7f4a8c706af7395044ab44513630c814a8d9634757020f03824d1dae6","target":"record","created_at":"2026-07-05T07:51:39Z","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":"695eed76849b1dd3ddbf713e2eee8a0bf5d87d173d5b5d9ceb8e98e931c2f98b","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2024-02-24T05:34:43Z","title_canon_sha256":"492fdfafbaeed0b5b06a47fe9daf92a1cab7b3a0b74f57ecf8edb5cc18189b45"},"schema_version":"1.0","source":{"id":"2402.15727","kind":"arxiv","version":2}},"canonical_sha256":"94c5a072d642552f9bc8c891fe81854dc38d6f0598d0dab6d0bee4b4d5534016","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"94c5a072d642552f9bc8c891fe81854dc38d6f0598d0dab6d0bee4b4d5534016","first_computed_at":"2026-07-05T07:51:39.857598Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:51:39.857598Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XZ98TWw3DbSH+Lb80iSi1yicrMILUvrtu/505OQR8WQOQxcVDfPiJcQ3fW9gqJNFORzu0rW4iQc3sY1lCu1uCA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:51:39.858028Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.15727","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7f3f18b7f4a8c706af7395044ab44513630c814a8d9634757020f03824d1dae6","sha256:a534cff4846d9c43139adec18e268bb7614d3cb5185d249e21bd4dc70db674bd"],"state_sha256":"62daaf576df4e0e350a718d3a4f28dea656014acc4afcbe84773653984671eb1"}