{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4G5LQYQNINWXPW4YKBIQ5X4VGG","short_pith_number":"pith:4G5LQYQN","schema_version":"1.0","canonical_sha256":"e1bab8620d436d77db9850510edf95318931b5e11c4dbc42148dbeebb23eadf0","source":{"kind":"arxiv","id":"2401.09798","version":3},"attestation_state":"computed","paper":{"title":"All in How You Ask for It: Simple Black-Box Method for Jailbreak Attacks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CY"],"primary_cat":"cs.CL","authors_text":"Kazuhiro Takemoto","submitted_at":"2024-01-18T08:36:54Z","abstract_excerpt":"Large Language Models (LLMs), such as ChatGPT, encounter `jailbreak' challenges, wherein safeguards are circumvented to generate ethically harmful prompts. This study introduces a straightforward black-box method for efficiently crafting jailbreak prompts, addressing the significant complexity and computational costs associated with conventional methods. Our technique iteratively transforms harmful prompts into benign expressions directly utilizing the target LLM, predicated on the hypothesis that LLMs can autonomously generate expressions that evade safeguards. Through experiments conducted w"},"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":"2401.09798","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-18T08:36:54Z","cross_cats_sorted":["cs.AI","cs.CY"],"title_canon_sha256":"e62fe8e65618dd3bc97295f6b43a556144e2208bd711b72be46ac68883fd1eb2","abstract_canon_sha256":"64faaadfc5e75e3bb280d613fe074d7d6e31fabf55c0cbbbb7b4df6eb2151908"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:11:23.003920Z","signature_b64":"FYe04eD/Oc/UbEQQ1xAWygoX1XogtK3Q6NAJfr7OTwP0ly2BcLDux+iTrp2NRW6WeQU9OkVzOm4eMSD3iEmPAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e1bab8620d436d77db9850510edf95318931b5e11c4dbc42148dbeebb23eadf0","last_reissued_at":"2026-07-05T08:11:23.003497Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:11:23.003497Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"All in How You Ask for It: Simple Black-Box Method for Jailbreak Attacks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CY"],"primary_cat":"cs.CL","authors_text":"Kazuhiro Takemoto","submitted_at":"2024-01-18T08:36:54Z","abstract_excerpt":"Large Language Models (LLMs), such as ChatGPT, encounter `jailbreak' challenges, wherein safeguards are circumvented to generate ethically harmful prompts. This study introduces a straightforward black-box method for efficiently crafting jailbreak prompts, addressing the significant complexity and computational costs associated with conventional methods. Our technique iteratively transforms harmful prompts into benign expressions directly utilizing the target LLM, predicated on the hypothesis that LLMs can autonomously generate expressions that evade safeguards. Through experiments conducted w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.09798","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/2401.09798/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":"2401.09798","created_at":"2026-07-05T08:11:23.003544+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.09798v3","created_at":"2026-07-05T08:11:23.003544+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.09798","created_at":"2026-07-05T08:11:23.003544+00:00"},{"alias_kind":"pith_short_12","alias_value":"4G5LQYQNINWX","created_at":"2026-07-05T08:11:23.003544+00:00"},{"alias_kind":"pith_short_16","alias_value":"4G5LQYQNINWXPW4Y","created_at":"2026-07-05T08:11:23.003544+00:00"},{"alias_kind":"pith_short_8","alias_value":"4G5LQYQN","created_at":"2026-07-05T08:11:23.003544+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2404.01318","citing_title":"JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2407.04295","citing_title":"Jailbreak Attacks and Defenses Against Large Language Models: A Survey","ref_index":88,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4G5LQYQNINWXPW4YKBIQ5X4VGG","json":"https://pith.science/pith/4G5LQYQNINWXPW4YKBIQ5X4VGG.json","graph_json":"https://pith.science/api/pith-number/4G5LQYQNINWXPW4YKBIQ5X4VGG/graph.json","events_json":"https://pith.science/api/pith-number/4G5LQYQNINWXPW4YKBIQ5X4VGG/events.json","paper":"https://pith.science/paper/4G5LQYQN"},"agent_actions":{"view_html":"https://pith.science/pith/4G5LQYQNINWXPW4YKBIQ5X4VGG","download_json":"https://pith.science/pith/4G5LQYQNINWXPW4YKBIQ5X4VGG.json","view_paper":"https://pith.science/paper/4G5LQYQN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.09798&json=true","fetch_graph":"https://pith.science/api/pith-number/4G5LQYQNINWXPW4YKBIQ5X4VGG/graph.json","fetch_events":"https://pith.science/api/pith-number/4G5LQYQNINWXPW4YKBIQ5X4VGG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4G5LQYQNINWXPW4YKBIQ5X4VGG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4G5LQYQNINWXPW4YKBIQ5X4VGG/action/storage_attestation","attest_author":"https://pith.science/pith/4G5LQYQNINWXPW4YKBIQ5X4VGG/action/author_attestation","sign_citation":"https://pith.science/pith/4G5LQYQNINWXPW4YKBIQ5X4VGG/action/citation_signature","submit_replication":"https://pith.science/pith/4G5LQYQNINWXPW4YKBIQ5X4VGG/action/replication_record"}},"created_at":"2026-07-05T08:11:23.003544+00:00","updated_at":"2026-07-05T08:11:23.003544+00:00"}