{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:L47TUNPKLUQB2ETFLISFHH4SDP","short_pith_number":"pith:L47TUNPK","schema_version":"1.0","canonical_sha256":"5f3f3a35ea5d201d12655a24539f921bf7bcd487bc7e9e95d64ab89aa3247735","source":{"kind":"arxiv","id":"2409.17699","version":3},"attestation_state":"computed","paper":{"title":"MoJE: Mixture of Jailbreak Experts, Naive Tabular Classifiers as Guard for Prompt Attacks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CR","authors_text":"Ambrish Rawat, Giandomenico Cornacchia, Giulio Zizzo, Kieran Fraser, Mark Purcell, Muhammad Zaid Hameed","submitted_at":"2024-09-26T10:12:19Z","abstract_excerpt":"The proliferation of Large Language Models (LLMs) in diverse applications underscores the pressing need for robust security measures to thwart potential jailbreak attacks. These attacks exploit vulnerabilities within LLMs, endanger data integrity and user privacy. Guardrails serve as crucial protective mechanisms against such threats, but existing models often fall short in terms of both detection accuracy, and computational efficiency. This paper advocates for the significance of jailbreak attack prevention on LLMs, and emphasises the role of input guardrails in safeguarding these models. We "},"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":"2409.17699","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-09-26T10:12:19Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"26725fb1e2d8256527cecdd2324ed8c3bb5729db71ccc1168df7d3022a6d395a","abstract_canon_sha256":"c975f12de6d41a35662e792da98287ab041ff47d4256d9d26ed7c687a746cb87"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:15:37.988302Z","signature_b64":"G3zPCCaitQMfn9V6UnJuztL0cOSDfVrsiTDCVDSylSJIRIfdHeP1r3RRcN4Xdym7HQ50tMLs2qCUN2eqgj7zDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f3f3a35ea5d201d12655a24539f921bf7bcd487bc7e9e95d64ab89aa3247735","last_reissued_at":"2026-07-05T09:15:37.987809Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:15:37.987809Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MoJE: Mixture of Jailbreak Experts, Naive Tabular Classifiers as Guard for Prompt Attacks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CR","authors_text":"Ambrish Rawat, Giandomenico Cornacchia, Giulio Zizzo, Kieran Fraser, Mark Purcell, Muhammad Zaid Hameed","submitted_at":"2024-09-26T10:12:19Z","abstract_excerpt":"The proliferation of Large Language Models (LLMs) in diverse applications underscores the pressing need for robust security measures to thwart potential jailbreak attacks. These attacks exploit vulnerabilities within LLMs, endanger data integrity and user privacy. Guardrails serve as crucial protective mechanisms against such threats, but existing models often fall short in terms of both detection accuracy, and computational efficiency. This paper advocates for the significance of jailbreak attack prevention on LLMs, and emphasises the role of input guardrails in safeguarding these models. We "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.17699","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/2409.17699/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":"2409.17699","created_at":"2026-07-05T09:15:37.987872+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.17699v3","created_at":"2026-07-05T09:15:37.987872+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.17699","created_at":"2026-07-05T09:15:37.987872+00:00"},{"alias_kind":"pith_short_12","alias_value":"L47TUNPKLUQB","created_at":"2026-07-05T09:15:37.987872+00:00"},{"alias_kind":"pith_short_16","alias_value":"L47TUNPKLUQB2ETF","created_at":"2026-07-05T09:15:37.987872+00:00"},{"alias_kind":"pith_short_8","alias_value":"L47TUNPK","created_at":"2026-07-05T09:15:37.987872+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/L47TUNPKLUQB2ETFLISFHH4SDP","json":"https://pith.science/pith/L47TUNPKLUQB2ETFLISFHH4SDP.json","graph_json":"https://pith.science/api/pith-number/L47TUNPKLUQB2ETFLISFHH4SDP/graph.json","events_json":"https://pith.science/api/pith-number/L47TUNPKLUQB2ETFLISFHH4SDP/events.json","paper":"https://pith.science/paper/L47TUNPK"},"agent_actions":{"view_html":"https://pith.science/pith/L47TUNPKLUQB2ETFLISFHH4SDP","download_json":"https://pith.science/pith/L47TUNPKLUQB2ETFLISFHH4SDP.json","view_paper":"https://pith.science/paper/L47TUNPK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.17699&json=true","fetch_graph":"https://pith.science/api/pith-number/L47TUNPKLUQB2ETFLISFHH4SDP/graph.json","fetch_events":"https://pith.science/api/pith-number/L47TUNPKLUQB2ETFLISFHH4SDP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L47TUNPKLUQB2ETFLISFHH4SDP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L47TUNPKLUQB2ETFLISFHH4SDP/action/storage_attestation","attest_author":"https://pith.science/pith/L47TUNPKLUQB2ETFLISFHH4SDP/action/author_attestation","sign_citation":"https://pith.science/pith/L47TUNPKLUQB2ETFLISFHH4SDP/action/citation_signature","submit_replication":"https://pith.science/pith/L47TUNPKLUQB2ETFLISFHH4SDP/action/replication_record"}},"created_at":"2026-07-05T09:15:37.987872+00:00","updated_at":"2026-07-05T09:15:37.987872+00:00"}