{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:S7O6ZDVWTQKWFBY7DDND2WWM5I","short_pith_number":"pith:S7O6ZDVW","schema_version":"1.0","canonical_sha256":"97ddec8eb69c1562871f18da3d5accea246311a392d646fa41db55fadfc4cd29","source":{"kind":"arxiv","id":"2403.17336","version":2},"attestation_state":"computed","paper":{"title":"Don't Listen To Me: Understanding and Exploring Jailbreak Prompts of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CR","authors_text":"Chaowei Xiao, Ning Zhang, Shunning Liang, Xiaogeng Liu, Zach Cameron, Zhiyuan Yu","submitted_at":"2024-03-26T02:47:42Z","abstract_excerpt":"Recent advancements in generative AI have enabled ubiquitous access to large language models (LLMs). Empowered by their exceptional capabilities to understand and generate human-like text, these models are being increasingly integrated into our society. At the same time, there are also concerns on the potential misuse of this powerful technology, prompting defensive measures from service providers. To overcome such protection, jailbreaking prompts have recently emerged as one of the most effective mechanisms to circumvent security restrictions and elicit harmful content originally designed 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":"2403.17336","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-03-26T02:47:42Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"164d96052b23adacd305252618896aab79df8395453b509b93d1bee955b62b2d","abstract_canon_sha256":"9ddbf728962aad9e535f4518dccca07124d5b524545447512d68873071b7eaf7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:13:51.134645Z","signature_b64":"n+LPu8MqnoSLlZmrqMoHn/PZI2njycZ8tiacAVE6E4RAg/EtcmW1t/iPVXAl/UarbndporxfEazrst5zdHGNBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"97ddec8eb69c1562871f18da3d5accea246311a392d646fa41db55fadfc4cd29","last_reissued_at":"2026-07-05T09:13:51.134133Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:13:51.134133Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Don't Listen To Me: Understanding and Exploring Jailbreak Prompts of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CR","authors_text":"Chaowei Xiao, Ning Zhang, Shunning Liang, Xiaogeng Liu, Zach Cameron, Zhiyuan Yu","submitted_at":"2024-03-26T02:47:42Z","abstract_excerpt":"Recent advancements in generative AI have enabled ubiquitous access to large language models (LLMs). Empowered by their exceptional capabilities to understand and generate human-like text, these models are being increasingly integrated into our society. At the same time, there are also concerns on the potential misuse of this powerful technology, prompting defensive measures from service providers. To overcome such protection, jailbreaking prompts have recently emerged as one of the most effective mechanisms to circumvent security restrictions and elicit harmful content originally designed to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.17336","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/2403.17336/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":"2403.17336","created_at":"2026-07-05T09:13:51.134188+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.17336v2","created_at":"2026-07-05T09:13:51.134188+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.17336","created_at":"2026-07-05T09:13:51.134188+00:00"},{"alias_kind":"pith_short_12","alias_value":"S7O6ZDVWTQKW","created_at":"2026-07-05T09:13:51.134188+00:00"},{"alias_kind":"pith_short_16","alias_value":"S7O6ZDVWTQKWFBY7","created_at":"2026-07-05T09:13:51.134188+00:00"},{"alias_kind":"pith_short_8","alias_value":"S7O6ZDVW","created_at":"2026-07-05T09:13:51.134188+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.11229","citing_title":"Comment and Control: Hijacking Agentic Workflows via Context-Grounded Evolution","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07727","citing_title":"TrajGuard: Streaming Hidden-state Trajectory Detection for Decoding-time Jailbreak Defense","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2604.28053","citing_title":"To Build or Not to Build? Factors that Lead to Non-Development or Abandonment of AI Systems","ref_index":176,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S7O6ZDVWTQKWFBY7DDND2WWM5I","json":"https://pith.science/pith/S7O6ZDVWTQKWFBY7DDND2WWM5I.json","graph_json":"https://pith.science/api/pith-number/S7O6ZDVWTQKWFBY7DDND2WWM5I/graph.json","events_json":"https://pith.science/api/pith-number/S7O6ZDVWTQKWFBY7DDND2WWM5I/events.json","paper":"https://pith.science/paper/S7O6ZDVW"},"agent_actions":{"view_html":"https://pith.science/pith/S7O6ZDVWTQKWFBY7DDND2WWM5I","download_json":"https://pith.science/pith/S7O6ZDVWTQKWFBY7DDND2WWM5I.json","view_paper":"https://pith.science/paper/S7O6ZDVW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.17336&json=true","fetch_graph":"https://pith.science/api/pith-number/S7O6ZDVWTQKWFBY7DDND2WWM5I/graph.json","fetch_events":"https://pith.science/api/pith-number/S7O6ZDVWTQKWFBY7DDND2WWM5I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S7O6ZDVWTQKWFBY7DDND2WWM5I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S7O6ZDVWTQKWFBY7DDND2WWM5I/action/storage_attestation","attest_author":"https://pith.science/pith/S7O6ZDVWTQKWFBY7DDND2WWM5I/action/author_attestation","sign_citation":"https://pith.science/pith/S7O6ZDVWTQKWFBY7DDND2WWM5I/action/citation_signature","submit_replication":"https://pith.science/pith/S7O6ZDVWTQKWFBY7DDND2WWM5I/action/replication_record"}},"created_at":"2026-07-05T09:13:51.134188+00:00","updated_at":"2026-07-05T09:13:51.134188+00:00"}