{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7TZ3QQR4DYJEZGSWPAVNAJ7FAV","short_pith_number":"pith:7TZ3QQR4","schema_version":"1.0","canonical_sha256":"fcf3b8423c1e124c9a56782ad027e505705c835afe51bfe635e7c06cf908dd88","source":{"kind":"arxiv","id":"2501.01335","version":1},"attestation_state":"computed","paper":{"title":"CySecBench: Generative AI-based CyberSecurity-focused Prompt Dataset for Benchmarking Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CR","authors_text":"Ahmed Mohamed Hussain, Johan Wahr\\'eus, Panos Papadimitratos","submitted_at":"2025-01-02T16:37:04Z","abstract_excerpt":"Numerous studies have investigated methods for jailbreaking Large Language Models (LLMs) to generate harmful content. Typically, these methods are evaluated using datasets of malicious prompts designed to bypass security policies established by LLM providers. However, the generally broad scope and open-ended nature of existing datasets can complicate the assessment of jailbreaking effectiveness, particularly in specific domains, notably cybersecurity. To address this issue, we present and publicly release CySecBench, a comprehensive dataset containing 12662 prompts specifically designed to eva"},"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":"2501.01335","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2025-01-02T16:37:04Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"34c447685068895bb6276ef3f478602efb78a1ba9b5199f1caf7790071ad96a2","abstract_canon_sha256":"5218753a60f6f4d1d4bd1933542d61400ab6fefd01c83ea8cdb9c29cbe4be2ba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:56:18.368790Z","signature_b64":"MoRkQUXGt/11jribcHsa/8IT1JYj6/YoUoDn9Rywe/VgmINlO9N4oqthICSweqqwIIHsfsaP2tbTJKP0kJKvCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fcf3b8423c1e124c9a56782ad027e505705c835afe51bfe635e7c06cf908dd88","last_reissued_at":"2026-07-05T09:56:18.368249Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:56:18.368249Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CySecBench: Generative AI-based CyberSecurity-focused Prompt Dataset for Benchmarking Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CR","authors_text":"Ahmed Mohamed Hussain, Johan Wahr\\'eus, Panos Papadimitratos","submitted_at":"2025-01-02T16:37:04Z","abstract_excerpt":"Numerous studies have investigated methods for jailbreaking Large Language Models (LLMs) to generate harmful content. Typically, these methods are evaluated using datasets of malicious prompts designed to bypass security policies established by LLM providers. However, the generally broad scope and open-ended nature of existing datasets can complicate the assessment of jailbreaking effectiveness, particularly in specific domains, notably cybersecurity. To address this issue, we present and publicly release CySecBench, a comprehensive dataset containing 12662 prompts specifically designed to eva"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.01335","kind":"arxiv","version":1},"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/2501.01335/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":"2501.01335","created_at":"2026-07-05T09:56:18.368324+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.01335v1","created_at":"2026-07-05T09:56:18.368324+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.01335","created_at":"2026-07-05T09:56:18.368324+00:00"},{"alias_kind":"pith_short_12","alias_value":"7TZ3QQR4DYJE","created_at":"2026-07-05T09:56:18.368324+00:00"},{"alias_kind":"pith_short_16","alias_value":"7TZ3QQR4DYJEZGSW","created_at":"2026-07-05T09:56:18.368324+00:00"},{"alias_kind":"pith_short_8","alias_value":"7TZ3QQR4","created_at":"2026-07-05T09:56:18.368324+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.28146","citing_title":"Cybersecurity AI (CAI) Dataset","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28734","citing_title":"Code as a Weapon: A Consensus-Labeled Prompt Bank for Measuring Coding-Model Compliance with Malicious-Code Requests","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20351","citing_title":"Refusal Evaluation in Coding LLMs and Code Agents: A Systematic Review of Thirteen Malicious-Code Prompt Corpora (2023-2025)","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2512.21110","citing_title":"Beyond Context: Large Language Models' Failure to Grasp Users' Intent","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03179","citing_title":"A Validated Prompt Bank for Malicious Code Generation: Separating Executable Weapons from Security Knowledge in 1,554 Consensus-Labeled Prompts","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7TZ3QQR4DYJEZGSWPAVNAJ7FAV","json":"https://pith.science/pith/7TZ3QQR4DYJEZGSWPAVNAJ7FAV.json","graph_json":"https://pith.science/api/pith-number/7TZ3QQR4DYJEZGSWPAVNAJ7FAV/graph.json","events_json":"https://pith.science/api/pith-number/7TZ3QQR4DYJEZGSWPAVNAJ7FAV/events.json","paper":"https://pith.science/paper/7TZ3QQR4"},"agent_actions":{"view_html":"https://pith.science/pith/7TZ3QQR4DYJEZGSWPAVNAJ7FAV","download_json":"https://pith.science/pith/7TZ3QQR4DYJEZGSWPAVNAJ7FAV.json","view_paper":"https://pith.science/paper/7TZ3QQR4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.01335&json=true","fetch_graph":"https://pith.science/api/pith-number/7TZ3QQR4DYJEZGSWPAVNAJ7FAV/graph.json","fetch_events":"https://pith.science/api/pith-number/7TZ3QQR4DYJEZGSWPAVNAJ7FAV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7TZ3QQR4DYJEZGSWPAVNAJ7FAV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7TZ3QQR4DYJEZGSWPAVNAJ7FAV/action/storage_attestation","attest_author":"https://pith.science/pith/7TZ3QQR4DYJEZGSWPAVNAJ7FAV/action/author_attestation","sign_citation":"https://pith.science/pith/7TZ3QQR4DYJEZGSWPAVNAJ7FAV/action/citation_signature","submit_replication":"https://pith.science/pith/7TZ3QQR4DYJEZGSWPAVNAJ7FAV/action/replication_record"}},"created_at":"2026-07-05T09:56:18.368324+00:00","updated_at":"2026-07-05T09:56:18.368324+00:00"}