{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LTKGHHOT4XY4BLJVUBJUPX4IGP","short_pith_number":"pith:LTKGHHOT","schema_version":"1.0","canonical_sha256":"5cd4639dd3e5f1c0ad35a05347df8833cf2e983463f1bdc7da0e23be6ff6e1be","source":{"kind":"arxiv","id":"2501.13411","version":1},"attestation_state":"computed","paper":{"title":"VulnBot: Autonomous Penetration Testing for A Multi-Agent Collaborative Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Bingzhen Wu, Die Hu, He Kong, Jingguo Ge, Liangxiong Li, Tong Li","submitted_at":"2025-01-23T06:33:05Z","abstract_excerpt":"Penetration testing is a vital practice for identifying and mitigating vulnerabilities in cybersecurity systems, but its manual execution is labor-intensive and time-consuming. Existing large language model (LLM)-assisted or automated penetration testing approaches often suffer from inefficiencies, such as a lack of contextual understanding and excessive, unstructured data generation. This paper presents VulnBot, an automated penetration testing framework that leverages LLMs to simulate the collaborative workflow of human penetration testing teams through a multi-agent system. To address the i"},"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":"2501.13411","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-01-23T06:33:05Z","cross_cats_sorted":[],"title_canon_sha256":"fa63daa6bec21cc28ce11fcc8961b220d60ff8da71bdd04433421e5bfb84cc1d","abstract_canon_sha256":"adab5e9488fa75bb03080b7ac877170017d5f8f104c14aa6a28822c32d143156"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:04:28.144963Z","signature_b64":"mtTuB7Q6iFqNf5Fx3bAj0PS705xnwsvDPKfUGgaN3oE1WJA81q/BXn1aMVR1ZUghDcZ7NLexG8VebrR5d/vwBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5cd4639dd3e5f1c0ad35a05347df8833cf2e983463f1bdc7da0e23be6ff6e1be","last_reissued_at":"2026-07-05T10:04:28.144479Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:04:28.144479Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VulnBot: Autonomous Penetration Testing for A Multi-Agent Collaborative Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Bingzhen Wu, Die Hu, He Kong, Jingguo Ge, Liangxiong Li, Tong Li","submitted_at":"2025-01-23T06:33:05Z","abstract_excerpt":"Penetration testing is a vital practice for identifying and mitigating vulnerabilities in cybersecurity systems, but its manual execution is labor-intensive and time-consuming. Existing large language model (LLM)-assisted or automated penetration testing approaches often suffer from inefficiencies, such as a lack of contextual understanding and excessive, unstructured data generation. This paper presents VulnBot, an automated penetration testing framework that leverages LLMs to simulate the collaborative workflow of human penetration testing teams through a multi-agent system. To address the i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.13411","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/2501.13411/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":"2501.13411","created_at":"2026-07-05T10:04:28.144540+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.13411v1","created_at":"2026-07-05T10:04:28.144540+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.13411","created_at":"2026-07-05T10:04:28.144540+00:00"},{"alias_kind":"pith_short_12","alias_value":"LTKGHHOT4XY4","created_at":"2026-07-05T10:04:28.144540+00:00"},{"alias_kind":"pith_short_16","alias_value":"LTKGHHOT4XY4BLJV","created_at":"2026-07-05T10:04:28.144540+00:00"},{"alias_kind":"pith_short_8","alias_value":"LTKGHHOT","created_at":"2026-07-05T10:04:28.144540+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07158","citing_title":"Synthetic APTs: the Collapse of TTP-Based Attribution","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05567","citing_title":"ZERO-APT: A Closed-Loop Adversarial Framework for LLM-Driven Automated Penetration Testing under Intelligent Defense","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30479","citing_title":"COHORT: Collaborative Orchestration for Hardening via Offensive Replay on Emulated Topologies","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26195","citing_title":"CyberEvolver: Structured Self-Evolution for Cybersecurity Agents On the Fly","ref_index":29,"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":7,"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":8,"is_internal_anchor":false},{"citing_arxiv_id":"2509.13021","citing_title":"xOffense: An Autonomous Multi-Agent Framework for Penetration Testing with Domain-Adapted Large Language Models","ref_index":9,"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":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24184","citing_title":"Dynamic Cyber Ranges","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04499","citing_title":"Pen-Strategist: A Reasoning Framework for Penetration Testing Strategy Formation and Analysis","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05719","citing_title":"Hackers or Hallucinators? A Comprehensive Analysis of LLM-Based Automated Penetration Testing","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14317","citing_title":"Challenges and Future Directions in Agentic Reverse Engineering Systems","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LTKGHHOT4XY4BLJVUBJUPX4IGP","json":"https://pith.science/pith/LTKGHHOT4XY4BLJVUBJUPX4IGP.json","graph_json":"https://pith.science/api/pith-number/LTKGHHOT4XY4BLJVUBJUPX4IGP/graph.json","events_json":"https://pith.science/api/pith-number/LTKGHHOT4XY4BLJVUBJUPX4IGP/events.json","paper":"https://pith.science/paper/LTKGHHOT"},"agent_actions":{"view_html":"https://pith.science/pith/LTKGHHOT4XY4BLJVUBJUPX4IGP","download_json":"https://pith.science/pith/LTKGHHOT4XY4BLJVUBJUPX4IGP.json","view_paper":"https://pith.science/paper/LTKGHHOT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.13411&json=true","fetch_graph":"https://pith.science/api/pith-number/LTKGHHOT4XY4BLJVUBJUPX4IGP/graph.json","fetch_events":"https://pith.science/api/pith-number/LTKGHHOT4XY4BLJVUBJUPX4IGP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LTKGHHOT4XY4BLJVUBJUPX4IGP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LTKGHHOT4XY4BLJVUBJUPX4IGP/action/storage_attestation","attest_author":"https://pith.science/pith/LTKGHHOT4XY4BLJVUBJUPX4IGP/action/author_attestation","sign_citation":"https://pith.science/pith/LTKGHHOT4XY4BLJVUBJUPX4IGP/action/citation_signature","submit_replication":"https://pith.science/pith/LTKGHHOT4XY4BLJVUBJUPX4IGP/action/replication_record"}},"created_at":"2026-07-05T10:04:28.144540+00:00","updated_at":"2026-07-05T10:04:28.144540+00:00"}