{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:T5BEEEN3NWQ2EE3U7QVLVMJSTP","short_pith_number":"pith:T5BEEEN3","schema_version":"1.0","canonical_sha256":"9f424211bb6da1a21374fc2abab1329bfa239beb593da7b862a65b6a3838396a","source":{"kind":"arxiv","id":"2403.00292","version":2},"attestation_state":"computed","paper":{"title":"Enhancing Jailbreak Attacks with Diversity Guidance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dinghao Jing, Xiaojun Wan, Xu Zhang","submitted_at":"2024-03-01T05:28:06Z","abstract_excerpt":"As large language models(LLMs) become commonplace in practical applications, the security issues of LLMs have attracted societal concerns. Although extensive efforts have been made to safety alignment, LLMs remain vulnerable to jailbreak attacks. We find that redundant computations limit the performance of existing jailbreak attack methods. Therefore, we propose DPP-based Stochastic Trigger Searching (DSTS), a new optimization algorithm for jailbreak attacks. DSTS incorporates diversity guidance through techniques including stochastic gradient search and DPP selection during optimization. Deta"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2403.00292","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-01T05:28:06Z","cross_cats_sorted":[],"title_canon_sha256":"67a9e15602f26a58e5cbf0c63783a16edae38bb0b5eaa45f9b01d93dc0ffcd69","abstract_canon_sha256":"544d298df204201626e9d6a8f5c714317d03ef5a342b85c4ca0fb2feb5eb5c2d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:09:03.132366Z","signature_b64":"y1rnzC7PwR9ogyNj6x6JsbM7xGTNGJNXjmGY5Ii2XIqknn+wnLIDvc4xNsJO72mg8QOtsr198IXkKWSOgd1DBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f424211bb6da1a21374fc2abab1329bfa239beb593da7b862a65b6a3838396a","last_reissued_at":"2026-07-05T09:09:03.131826Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:09:03.131826Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Jailbreak Attacks with Diversity Guidance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dinghao Jing, Xiaojun Wan, Xu Zhang","submitted_at":"2024-03-01T05:28:06Z","abstract_excerpt":"As large language models(LLMs) become commonplace in practical applications, the security issues of LLMs have attracted societal concerns. Although extensive efforts have been made to safety alignment, LLMs remain vulnerable to jailbreak attacks. We find that redundant computations limit the performance of existing jailbreak attack methods. Therefore, we propose DPP-based Stochastic Trigger Searching (DSTS), a new optimization algorithm for jailbreak attacks. DSTS incorporates diversity guidance through techniques including stochastic gradient search and DPP selection during optimization. Deta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.00292","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2403.00292/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2403.00292","created_at":"2026-07-05T09:09:03.131884+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.00292v2","created_at":"2026-07-05T09:09:03.131884+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.00292","created_at":"2026-07-05T09:09:03.131884+00:00"},{"alias_kind":"pith_short_12","alias_value":"T5BEEEN3NWQ2","created_at":"2026-07-05T09:09:03.131884+00:00"},{"alias_kind":"pith_short_16","alias_value":"T5BEEEN3NWQ2EE3U","created_at":"2026-07-05T09:09:03.131884+00:00"},{"alias_kind":"pith_short_8","alias_value":"T5BEEEN3","created_at":"2026-07-05T09:09:03.131884+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.21859","citing_title":"Principled Content Selection to Generate Diverse and Personalized Multi-Document Summaries","ref_index":56,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T5BEEEN3NWQ2EE3U7QVLVMJSTP","json":"https://pith.science/pith/T5BEEEN3NWQ2EE3U7QVLVMJSTP.json","graph_json":"https://pith.science/api/pith-number/T5BEEEN3NWQ2EE3U7QVLVMJSTP/graph.json","events_json":"https://pith.science/api/pith-number/T5BEEEN3NWQ2EE3U7QVLVMJSTP/events.json","paper":"https://pith.science/paper/T5BEEEN3"},"agent_actions":{"view_html":"https://pith.science/pith/T5BEEEN3NWQ2EE3U7QVLVMJSTP","download_json":"https://pith.science/pith/T5BEEEN3NWQ2EE3U7QVLVMJSTP.json","view_paper":"https://pith.science/paper/T5BEEEN3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.00292&json=true","fetch_graph":"https://pith.science/api/pith-number/T5BEEEN3NWQ2EE3U7QVLVMJSTP/graph.json","fetch_events":"https://pith.science/api/pith-number/T5BEEEN3NWQ2EE3U7QVLVMJSTP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T5BEEEN3NWQ2EE3U7QVLVMJSTP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T5BEEEN3NWQ2EE3U7QVLVMJSTP/action/storage_attestation","attest_author":"https://pith.science/pith/T5BEEEN3NWQ2EE3U7QVLVMJSTP/action/author_attestation","sign_citation":"https://pith.science/pith/T5BEEEN3NWQ2EE3U7QVLVMJSTP/action/citation_signature","submit_replication":"https://pith.science/pith/T5BEEEN3NWQ2EE3U7QVLVMJSTP/action/replication_record"}},"created_at":"2026-07-05T09:09:03.131884+00:00","updated_at":"2026-07-05T09:09:03.131884+00:00"}