{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QUHUWX2WAFZUZU2BYL2OBXDLZ3","short_pith_number":"pith:QUHUWX2W","schema_version":"1.0","canonical_sha256":"850f4b5f5601734cd341c2f4e0dc6bcef07bf3bd1d1ecff55d96e4ecbc962a17","source":{"kind":"arxiv","id":"2410.03225","version":2},"attestation_state":"computed","paper":{"title":"AutoPenBench: Benchmarking Generative Agents for Penetration Testing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Alexander Delsanto, Giuseppe Siracusano, Idilio Drago, Luca Gioacchini, Marco Mellia, Roberto Bifulco","submitted_at":"2024-10-04T08:24:15Z","abstract_excerpt":"Generative AI agents, software systems powered by Large Language Models (LLMs), are emerging as a promising approach to automate cybersecurity tasks. Among the others, penetration testing is a challenging field due to the task complexity and the diverse strategies to simulate cyber-attacks. Despite growing interest and initial studies in automating penetration testing with generative agents, there remains a significant gap in the form of a comprehensive and standard framework for their evaluation and development. This paper introduces AutoPenBench, an open benchmark for evaluating generative a"},"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":"2410.03225","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2024-10-04T08:24:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d93f47cbbed5c5771d1a82c13d5e8a7cf7e14cbb9a687fd9020c038f015bac47","abstract_canon_sha256":"9bf1298db3bd706ad1ec31e8376c06e623a1d974c2c26e3524326fa50c6e2e87"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:27:05.425127Z","signature_b64":"ghwlIPEwxtnEDiDpPO6jRF5/d5uTg19URm5tJBfel6yMNmNAnSv+HLXaiq4YVBc6WUv8UIZJckAU3cD8D7weBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"850f4b5f5601734cd341c2f4e0dc6bcef07bf3bd1d1ecff55d96e4ecbc962a17","last_reissued_at":"2026-07-05T09:27:05.424652Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:27:05.424652Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AutoPenBench: Benchmarking Generative Agents for Penetration Testing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Alexander Delsanto, Giuseppe Siracusano, Idilio Drago, Luca Gioacchini, Marco Mellia, Roberto Bifulco","submitted_at":"2024-10-04T08:24:15Z","abstract_excerpt":"Generative AI agents, software systems powered by Large Language Models (LLMs), are emerging as a promising approach to automate cybersecurity tasks. Among the others, penetration testing is a challenging field due to the task complexity and the diverse strategies to simulate cyber-attacks. Despite growing interest and initial studies in automating penetration testing with generative agents, there remains a significant gap in the form of a comprehensive and standard framework for their evaluation and development. This paper introduces AutoPenBench, an open benchmark for evaluating generative a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.03225","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/2410.03225/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":"2410.03225","created_at":"2026-07-05T09:27:05.424713+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.03225v2","created_at":"2026-07-05T09:27:05.424713+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.03225","created_at":"2026-07-05T09:27:05.424713+00:00"},{"alias_kind":"pith_short_12","alias_value":"QUHUWX2WAFZU","created_at":"2026-07-05T09:27:05.424713+00:00"},{"alias_kind":"pith_short_16","alias_value":"QUHUWX2WAFZUZU2B","created_at":"2026-07-05T09:27:05.424713+00:00"},{"alias_kind":"pith_short_8","alias_value":"QUHUWX2W","created_at":"2026-07-05T09:27:05.424713+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.13079","citing_title":"The Emergence of Autonomous Penetration Capabilities in Large Language Model-Powered AI Systems","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.13079","citing_title":"The Emergence of Autonomous Penetration Capabilities in Large Language Model-Powered AI Systems","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26195","citing_title":"CyberEvolver: Structured Self-Evolution for Cybersecurity Agents On the Fly","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30096","citing_title":"How Reliable Are AI Attackers Against a Fixed Vulnerable Target? A 400-Run Empirical Study of LLM Penetration Testing Consistency","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2509.06921","citing_title":"Neuro-Symbolic AI for Cybersecurity: State of the Art, Challenges, and Opportunities","ref_index":174,"is_internal_anchor":false},{"citing_arxiv_id":"2512.22753","citing_title":"From Rookie to Expert: Manipulating LLMs for Automated Vulnerability Exploitation in Enterprise Software","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10834","citing_title":"From Controlled to the Wild: Evaluation of Pentesting Agents for the Real-World","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06486","citing_title":"Autonomous Adversary: Red-Teaming in the age of LLM","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QUHUWX2WAFZUZU2BYL2OBXDLZ3","json":"https://pith.science/pith/QUHUWX2WAFZUZU2BYL2OBXDLZ3.json","graph_json":"https://pith.science/api/pith-number/QUHUWX2WAFZUZU2BYL2OBXDLZ3/graph.json","events_json":"https://pith.science/api/pith-number/QUHUWX2WAFZUZU2BYL2OBXDLZ3/events.json","paper":"https://pith.science/paper/QUHUWX2W"},"agent_actions":{"view_html":"https://pith.science/pith/QUHUWX2WAFZUZU2BYL2OBXDLZ3","download_json":"https://pith.science/pith/QUHUWX2WAFZUZU2BYL2OBXDLZ3.json","view_paper":"https://pith.science/paper/QUHUWX2W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.03225&json=true","fetch_graph":"https://pith.science/api/pith-number/QUHUWX2WAFZUZU2BYL2OBXDLZ3/graph.json","fetch_events":"https://pith.science/api/pith-number/QUHUWX2WAFZUZU2BYL2OBXDLZ3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QUHUWX2WAFZUZU2BYL2OBXDLZ3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QUHUWX2WAFZUZU2BYL2OBXDLZ3/action/storage_attestation","attest_author":"https://pith.science/pith/QUHUWX2WAFZUZU2BYL2OBXDLZ3/action/author_attestation","sign_citation":"https://pith.science/pith/QUHUWX2WAFZUZU2BYL2OBXDLZ3/action/citation_signature","submit_replication":"https://pith.science/pith/QUHUWX2WAFZUZU2BYL2OBXDLZ3/action/replication_record"}},"created_at":"2026-07-05T09:27:05.424713+00:00","updated_at":"2026-07-05T09:27:05.424713+00:00"}