{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:RKPGH25NTLEGPHH6V23HTUO6RU","short_pith_number":"pith:RKPGH25N","schema_version":"1.0","canonical_sha256":"8a9e63ebad9ac8679cfeaeb679d1de8d0f127e5ee42e777e0470d7fc5dca5268","source":{"kind":"arxiv","id":"2308.06782","version":2},"attestation_state":"computed","paper":{"title":"PentestGPT: An LLM-empowered Automatic Penetration Testing Tool","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.SE","authors_text":"Gelei Deng, Martin Pinzger, Peng Liu, Stefan Rass, Tianwei Zhang, V\\'ictor Mayoral-Vilches, Yang Liu, Yi Liu, Yuan Xu, Yuekang Li","submitted_at":"2023-08-13T14:35:50Z","abstract_excerpt":"Penetration testing, a crucial industrial practice for ensuring system security, has traditionally resisted automation due to the extensive expertise required by human professionals. Large Language Models (LLMs) have shown significant advancements in various domains, and their emergent abilities suggest their potential to revolutionize industries. In this research, we evaluate the performance of LLMs on real-world penetration testing tasks using a robust benchmark created from test machines with platforms. Our findings reveal that while LLMs demonstrate proficiency in specific sub-tasks within"},"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":"2308.06782","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2023-08-13T14:35:50Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"0ccafb591f67a0447108c81c07f336aadd0267127232f3005395fbe8dc26ceac","abstract_canon_sha256":"1c783ee5e1f2169a7d4fcb50d59e3425220155064bb60c24a57e52070812b11f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:26:13.350796Z","signature_b64":"1jH/dZX+5/TbE014csQJJ7aMdf6aaCQDhSzaUXo8qcRLaHz4OqxHa3Xcb1dAziUVg1SzxuhnGmWG9tRxDWG5Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a9e63ebad9ac8679cfeaeb679d1de8d0f127e5ee42e777e0470d7fc5dca5268","last_reissued_at":"2026-07-05T08:26:13.350285Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:26:13.350285Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PentestGPT: An LLM-empowered Automatic Penetration Testing Tool","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.SE","authors_text":"Gelei Deng, Martin Pinzger, Peng Liu, Stefan Rass, Tianwei Zhang, V\\'ictor Mayoral-Vilches, Yang Liu, Yi Liu, Yuan Xu, Yuekang Li","submitted_at":"2023-08-13T14:35:50Z","abstract_excerpt":"Penetration testing, a crucial industrial practice for ensuring system security, has traditionally resisted automation due to the extensive expertise required by human professionals. Large Language Models (LLMs) have shown significant advancements in various domains, and their emergent abilities suggest their potential to revolutionize industries. In this research, we evaluate the performance of LLMs on real-world penetration testing tasks using a robust benchmark created from test machines with platforms. Our findings reveal that while LLMs demonstrate proficiency in specific sub-tasks within"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.06782","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/2308.06782/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":"2308.06782","created_at":"2026-07-05T08:26:13.350353+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.06782v2","created_at":"2026-07-05T08:26:13.350353+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.06782","created_at":"2026-07-05T08:26:13.350353+00:00"},{"alias_kind":"pith_short_12","alias_value":"RKPGH25NTLEG","created_at":"2026-07-05T08:26:13.350353+00:00"},{"alias_kind":"pith_short_16","alias_value":"RKPGH25NTLEGPHH6","created_at":"2026-07-05T08:26:13.350353+00:00"},{"alias_kind":"pith_short_8","alias_value":"RKPGH25N","created_at":"2026-07-05T08:26:13.350353+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":19,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2607.07774","citing_title":"ScopeJudge: Cost-Aware Pre-Execution Gating for Offensive Security Agents","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2607.07109","citing_title":"Certifying Ghosts: How Cybersecurity AI Agents Break the EU Cyber Resilience Act","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2606.07158","citing_title":"Synthetic APTs: the Collapse of TTP-Based Attribution","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31639","citing_title":"A Lifecycle and Application-Stack Survey of Large Language Model Vulnerabilities: Attacks, Risks, Defenses, and Open Problems","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29981","citing_title":"Hephaestus: Toward a Cybersecurity AI Scientist","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29124","citing_title":"CornerCase: Automated Extremal Testing of Protocol Implementations using LLMs","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26195","citing_title":"CyberEvolver: Structured Self-Evolution for Cybersecurity Agents On the Fly","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29269","citing_title":"HunterAgent: Neuro-Symbolic Attack Trace Reconstruction under Anti-Forensics","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29963","citing_title":"Honeyval: A Comprehensive Evaluation Framework for LLM-powered HTTP Honeypots","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17406","citing_title":"Rethinking Side-Channel Analysis: Automated Discovery and Analysis of Side-Channel Leakage with LLM-Assisted Agents","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17416","citing_title":"Benchmarking Mythos-Linked Bug Rediscovery","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2308.11432","citing_title":"A Survey on Large Language Model based Autonomous Agents","ref_index":125,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11003","citing_title":"The Authorization-Execution Gap Is a Major Safety and Security Problem in Open-World Agents","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27143","citing_title":"Enhancing Linux Privilege Escalation Attack Capabilities of Local LLM Agents","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06601","citing_title":"Patch2Vuln: Agentic Reconstruction of Vulnerabilities from Linux Distribution Binary Patches","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01186","citing_title":"Trace: Unmasking AI Attack Agents Through Terminal Behavior Fingerprinting","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06618","citing_title":"PoC-Adapt: Semantic-Aware Automated Vulnerability Reproduction with LLM Multi-Agents and Reinforcement Learning-Driven Adaptive Policy","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19031","citing_title":"SAGE: Signal-Amplified Guided Embeddings for LLM-based Vulnerability Detection","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02992","citing_title":"PHANTOM: Polymorphic Honeytoken Adaptation with Narrative-Tailored Organisational Mimicry","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RKPGH25NTLEGPHH6V23HTUO6RU","json":"https://pith.science/pith/RKPGH25NTLEGPHH6V23HTUO6RU.json","graph_json":"https://pith.science/api/pith-number/RKPGH25NTLEGPHH6V23HTUO6RU/graph.json","events_json":"https://pith.science/api/pith-number/RKPGH25NTLEGPHH6V23HTUO6RU/events.json","paper":"https://pith.science/paper/RKPGH25N"},"agent_actions":{"view_html":"https://pith.science/pith/RKPGH25NTLEGPHH6V23HTUO6RU","download_json":"https://pith.science/pith/RKPGH25NTLEGPHH6V23HTUO6RU.json","view_paper":"https://pith.science/paper/RKPGH25N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.06782&json=true","fetch_graph":"https://pith.science/api/pith-number/RKPGH25NTLEGPHH6V23HTUO6RU/graph.json","fetch_events":"https://pith.science/api/pith-number/RKPGH25NTLEGPHH6V23HTUO6RU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RKPGH25NTLEGPHH6V23HTUO6RU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RKPGH25NTLEGPHH6V23HTUO6RU/action/storage_attestation","attest_author":"https://pith.science/pith/RKPGH25NTLEGPHH6V23HTUO6RU/action/author_attestation","sign_citation":"https://pith.science/pith/RKPGH25NTLEGPHH6V23HTUO6RU/action/citation_signature","submit_replication":"https://pith.science/pith/RKPGH25NTLEGPHH6V23HTUO6RU/action/replication_record"}},"created_at":"2026-07-05T08:26:13.350353+00:00","updated_at":"2026-07-05T08:26:13.350353+00:00"}