{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ICWAAAGR2WQNEYYB4UYNOM23MX","short_pith_number":"pith:ICWAAAGR","schema_version":"1.0","canonical_sha256":"40ac0000d1d5a0d26301e530d7335b65ca30e4a644366f7c7c4a02cf4a4e6a3a","source":{"kind":"arxiv","id":"2406.09324","version":3},"attestation_state":"computed","paper":{"title":"Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CR","authors_text":"Fan Liu, Hao Liu, Zhao Xu","submitted_at":"2024-06-13T17:01:40Z","abstract_excerpt":"Although Large Language Models (LLMs) have demonstrated significant capabilities in executing complex tasks in a zero-shot manner, they are susceptible to jailbreak attacks and can be manipulated to produce harmful outputs. Recently, a growing body of research has categorized jailbreak attacks into token-level and prompt-level attacks. However, previous work primarily overlooks the diverse key factors of jailbreak attacks, with most studies concentrating on LLM vulnerabilities and lacking exploration of defense-enhanced LLMs. To address these issues, we introduced $\\textbf{JailTrickBench}$ to "},"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":"2406.09324","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CR","submitted_at":"2024-06-13T17:01:40Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"c01df6d7504c5080e9baba0d4e1b5531ad6882ac04f22214d4b7027789f04499","abstract_canon_sha256":"ca90b89755cec8299f847f140db5da4dd9191c0d7ccfde861fbbd292c02b05a7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:31:46.793263Z","signature_b64":"Jcwg4+4LrD6xHq1XjKkEOLNLZmlWbuzu4wDj4WkBjNBBmv5hv160xoVWYNVoTxY8fQ5IQvXAYw6u/3skazEXDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"40ac0000d1d5a0d26301e530d7335b65ca30e4a644366f7c7c4a02cf4a4e6a3a","last_reissued_at":"2026-07-05T09:31:46.792808Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:31:46.792808Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CR","authors_text":"Fan Liu, Hao Liu, Zhao Xu","submitted_at":"2024-06-13T17:01:40Z","abstract_excerpt":"Although Large Language Models (LLMs) have demonstrated significant capabilities in executing complex tasks in a zero-shot manner, they are susceptible to jailbreak attacks and can be manipulated to produce harmful outputs. Recently, a growing body of research has categorized jailbreak attacks into token-level and prompt-level attacks. However, previous work primarily overlooks the diverse key factors of jailbreak attacks, with most studies concentrating on LLM vulnerabilities and lacking exploration of defense-enhanced LLMs. To address these issues, we introduced $\\textbf{JailTrickBench}$ to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.09324","kind":"arxiv","version":3},"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/2406.09324/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":"2406.09324","created_at":"2026-07-05T09:31:46.792858+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.09324v3","created_at":"2026-07-05T09:31:46.792858+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.09324","created_at":"2026-07-05T09:31:46.792858+00:00"},{"alias_kind":"pith_short_12","alias_value":"ICWAAAGR2WQN","created_at":"2026-07-05T09:31:46.792858+00:00"},{"alias_kind":"pith_short_16","alias_value":"ICWAAAGR2WQNEYYB","created_at":"2026-07-05T09:31:46.792858+00:00"},{"alias_kind":"pith_short_8","alias_value":"ICWAAAGR","created_at":"2026-07-05T09:31:46.792858+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ICWAAAGR2WQNEYYB4UYNOM23MX","json":"https://pith.science/pith/ICWAAAGR2WQNEYYB4UYNOM23MX.json","graph_json":"https://pith.science/api/pith-number/ICWAAAGR2WQNEYYB4UYNOM23MX/graph.json","events_json":"https://pith.science/api/pith-number/ICWAAAGR2WQNEYYB4UYNOM23MX/events.json","paper":"https://pith.science/paper/ICWAAAGR"},"agent_actions":{"view_html":"https://pith.science/pith/ICWAAAGR2WQNEYYB4UYNOM23MX","download_json":"https://pith.science/pith/ICWAAAGR2WQNEYYB4UYNOM23MX.json","view_paper":"https://pith.science/paper/ICWAAAGR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.09324&json=true","fetch_graph":"https://pith.science/api/pith-number/ICWAAAGR2WQNEYYB4UYNOM23MX/graph.json","fetch_events":"https://pith.science/api/pith-number/ICWAAAGR2WQNEYYB4UYNOM23MX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ICWAAAGR2WQNEYYB4UYNOM23MX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ICWAAAGR2WQNEYYB4UYNOM23MX/action/storage_attestation","attest_author":"https://pith.science/pith/ICWAAAGR2WQNEYYB4UYNOM23MX/action/author_attestation","sign_citation":"https://pith.science/pith/ICWAAAGR2WQNEYYB4UYNOM23MX/action/citation_signature","submit_replication":"https://pith.science/pith/ICWAAAGR2WQNEYYB4UYNOM23MX/action/replication_record"}},"created_at":"2026-07-05T09:31:46.792858+00:00","updated_at":"2026-07-05T09:31:46.792858+00:00"}