{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:URMRAFQLC7CDGZFI5RJ5HRE4IW","short_pith_number":"pith:URMRAFQL","schema_version":"1.0","canonical_sha256":"a45910160b17c43364a8ec53d3c49c45b38e781d07e5de84035ebb2b26fa4246","source":{"kind":"arxiv","id":"2501.18632","version":2},"attestation_state":"computed","paper":{"title":"Towards Safe AI Clinicians: A Comprehensive Study on Large Language Model Jailbreaking in Healthcare","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CR","authors_text":"Hang Zhang, Qian Lou, Yanshan Wang","submitted_at":"2025-01-27T22:07:52Z","abstract_excerpt":"Large language models (LLMs) are increasingly utilized in healthcare applications. However, their deployment in clinical practice raises significant safety concerns, including the potential spread of harmful information. This study systematically assesses the vulnerabilities of seven LLMs to three advanced black-box jailbreaking techniques within medical contexts. To quantify the effectiveness of these techniques, we propose an automated and domain-adapted agentic evaluation pipeline. Experiment results indicate that leading commercial and open-source LLMs are highly vulnerable to medical jail"},"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":"2501.18632","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CR","submitted_at":"2025-01-27T22:07:52Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"e20345ccdfbbe59a4d55f91b8051aad1109777477ef3dfc38ffff2fefa3a234f","abstract_canon_sha256":"920af65a2c903f36bcf13769ce1b99c6c2eb55d317516b053fd90901e580cec6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:24:00.277883Z","signature_b64":"dsj6JYsVePqblaJ0XJ81CFPfpgjNVRTnUa0B7SN3EJIUBWjB5W6SRsEI6Yr4zwN6beZD2nDge0WL6VdhjOMGBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a45910160b17c43364a8ec53d3c49c45b38e781d07e5de84035ebb2b26fa4246","last_reissued_at":"2026-07-05T10:24:00.277429Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:24:00.277429Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Safe AI Clinicians: A Comprehensive Study on Large Language Model Jailbreaking in Healthcare","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CR","authors_text":"Hang Zhang, Qian Lou, Yanshan Wang","submitted_at":"2025-01-27T22:07:52Z","abstract_excerpt":"Large language models (LLMs) are increasingly utilized in healthcare applications. However, their deployment in clinical practice raises significant safety concerns, including the potential spread of harmful information. This study systematically assesses the vulnerabilities of seven LLMs to three advanced black-box jailbreaking techniques within medical contexts. To quantify the effectiveness of these techniques, we propose an automated and domain-adapted agentic evaluation pipeline. Experiment results indicate that leading commercial and open-source LLMs are highly vulnerable to medical jail"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.18632","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/2501.18632/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":"2501.18632","created_at":"2026-07-05T10:24:00.277481+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.18632v2","created_at":"2026-07-05T10:24:00.277481+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.18632","created_at":"2026-07-05T10:24:00.277481+00:00"},{"alias_kind":"pith_short_12","alias_value":"URMRAFQLC7CD","created_at":"2026-07-05T10:24:00.277481+00:00"},{"alias_kind":"pith_short_16","alias_value":"URMRAFQLC7CDGZFI","created_at":"2026-07-05T10:24:00.277481+00:00"},{"alias_kind":"pith_short_8","alias_value":"URMRAFQL","created_at":"2026-07-05T10:24:00.277481+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23884","citing_title":"One Year Later...The Harms Persist, But So Do We!","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2606.23884","citing_title":"One Year Later...The Harms Persist, But So Do We!","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/URMRAFQLC7CDGZFI5RJ5HRE4IW","json":"https://pith.science/pith/URMRAFQLC7CDGZFI5RJ5HRE4IW.json","graph_json":"https://pith.science/api/pith-number/URMRAFQLC7CDGZFI5RJ5HRE4IW/graph.json","events_json":"https://pith.science/api/pith-number/URMRAFQLC7CDGZFI5RJ5HRE4IW/events.json","paper":"https://pith.science/paper/URMRAFQL"},"agent_actions":{"view_html":"https://pith.science/pith/URMRAFQLC7CDGZFI5RJ5HRE4IW","download_json":"https://pith.science/pith/URMRAFQLC7CDGZFI5RJ5HRE4IW.json","view_paper":"https://pith.science/paper/URMRAFQL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.18632&json=true","fetch_graph":"https://pith.science/api/pith-number/URMRAFQLC7CDGZFI5RJ5HRE4IW/graph.json","fetch_events":"https://pith.science/api/pith-number/URMRAFQLC7CDGZFI5RJ5HRE4IW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/URMRAFQLC7CDGZFI5RJ5HRE4IW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/URMRAFQLC7CDGZFI5RJ5HRE4IW/action/storage_attestation","attest_author":"https://pith.science/pith/URMRAFQLC7CDGZFI5RJ5HRE4IW/action/author_attestation","sign_citation":"https://pith.science/pith/URMRAFQLC7CDGZFI5RJ5HRE4IW/action/citation_signature","submit_replication":"https://pith.science/pith/URMRAFQLC7CDGZFI5RJ5HRE4IW/action/replication_record"}},"created_at":"2026-07-05T10:24:00.277481+00:00","updated_at":"2026-07-05T10:24:00.277481+00:00"}