{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RMEJCKMKAES2TSKRR3IZJE2EUK","short_pith_number":"pith:RMEJCKMK","schema_version":"1.0","canonical_sha256":"8b0891298a0125a9c9518ed1949344a2bd8ed3e76993d5b0f18d287b04a73515","source":{"kind":"arxiv","id":"2403.01038","version":1},"attestation_state":"computed","paper":{"title":"AutoAttacker: A Large Language Model Guided System to Implement Automatic Cyber-attacks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Adith Swaminathan, David Marshall, Geoff McDonald, Jack W. Stokes, Jiacen Xu, Siyue Wang, Xuesong Bai, Zhou Li","submitted_at":"2024-03-02T00:10:45Z","abstract_excerpt":"Large language models (LLMs) have demonstrated impressive results on natural language tasks, and security researchers are beginning to employ them in both offensive and defensive systems. In cyber-security, there have been multiple research efforts that utilize LLMs focusing on the pre-breach stage of attacks like phishing and malware generation. However, so far there lacks a comprehensive study regarding whether LLM-based systems can be leveraged to simulate the post-breach stage of attacks that are typically human-operated, or \"hands-on-keyboard\" attacks, under various attack techniques and "},"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":"2403.01038","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2024-03-02T00:10:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"583b4d6c3c3939b794d2e2472e31d8df11602c93c53d572a3da7ddbd0dab4d27","abstract_canon_sha256":"ef81f8e83c035e0c331d5b94259ce12c6455e220dec650e920c0988f49ca4b26"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:51:15.409324Z","signature_b64":"svGIxYAa3J9aQC1h7Hw3TL6PannEvx7wa6kH/QscIDtEeeUlt9JcTmJ4pfaN0oKTHQH4qgPvqhx3mP1DdYplCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b0891298a0125a9c9518ed1949344a2bd8ed3e76993d5b0f18d287b04a73515","last_reissued_at":"2026-07-05T07:51:15.408871Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:51:15.408871Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AutoAttacker: A Large Language Model Guided System to Implement Automatic Cyber-attacks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Adith Swaminathan, David Marshall, Geoff McDonald, Jack W. Stokes, Jiacen Xu, Siyue Wang, Xuesong Bai, Zhou Li","submitted_at":"2024-03-02T00:10:45Z","abstract_excerpt":"Large language models (LLMs) have demonstrated impressive results on natural language tasks, and security researchers are beginning to employ them in both offensive and defensive systems. In cyber-security, there have been multiple research efforts that utilize LLMs focusing on the pre-breach stage of attacks like phishing and malware generation. However, so far there lacks a comprehensive study regarding whether LLM-based systems can be leveraged to simulate the post-breach stage of attacks that are typically human-operated, or \"hands-on-keyboard\" attacks, under various attack techniques and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.01038","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/2403.01038/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":"2403.01038","created_at":"2026-07-05T07:51:15.408928+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.01038v1","created_at":"2026-07-05T07:51:15.408928+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.01038","created_at":"2026-07-05T07:51:15.408928+00:00"},{"alias_kind":"pith_short_12","alias_value":"RMEJCKMKAES2","created_at":"2026-07-05T07:51:15.408928+00:00"},{"alias_kind":"pith_short_16","alias_value":"RMEJCKMKAES2TSKR","created_at":"2026-07-05T07:51:15.408928+00:00"},{"alias_kind":"pith_short_8","alias_value":"RMEJCKMK","created_at":"2026-07-05T07:51:15.408928+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":18,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25332","citing_title":"Decoupling Reconnaissance and Exploitation: Measuring the Capability Boundaries of LLM-Based Web Penetration Testing","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":12,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03811","citing_title":"AI Agents Enable Adaptive Computer Worms","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24949","citing_title":"APT-Agent: Automated Penetration Testing using Large Language Models","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21694","citing_title":"PocketAgents: A Manifest-Driven Library of Autonomous Defense Agents","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21773","citing_title":"HIDBench: Benchmarking Large Language Models for Host-Based Intrusion Detection","ref_index":7,"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":18,"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":34,"is_internal_anchor":false},{"citing_arxiv_id":"2412.04984","citing_title":"Frontier Models are Capable of In-context Scheming","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27143","citing_title":"Enhancing Linux Privilege Escalation Attack Capabilities of Local LLM Agents","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06486","citing_title":"Autonomous Adversary: Red-Teaming in the age of LLM","ref_index":6,"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":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00741","citing_title":"Self-Adaptive Multi-Agent LLM-Based Security Pattern Selection for IoT Systems","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07830","citing_title":"CyBiasBench: Benchmarking Bias in LLM Agents for Cyber-Attack Scenarios","ref_index":29,"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":121,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05440","citing_title":"LanG -- A Governance-Aware Agentic AI Platform for Unified Security Operations","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06019","citing_title":"CritBench: A Framework for Evaluating Cybersecurity Capabilities of Large Language Models in IEC 61850 Digital Substation Environments","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02346","citing_title":"APIOT: Autonomous Vulnerability Management Across Bare-Metal Industrial OT Networks","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RMEJCKMKAES2TSKRR3IZJE2EUK","json":"https://pith.science/pith/RMEJCKMKAES2TSKRR3IZJE2EUK.json","graph_json":"https://pith.science/api/pith-number/RMEJCKMKAES2TSKRR3IZJE2EUK/graph.json","events_json":"https://pith.science/api/pith-number/RMEJCKMKAES2TSKRR3IZJE2EUK/events.json","paper":"https://pith.science/paper/RMEJCKMK"},"agent_actions":{"view_html":"https://pith.science/pith/RMEJCKMKAES2TSKRR3IZJE2EUK","download_json":"https://pith.science/pith/RMEJCKMKAES2TSKRR3IZJE2EUK.json","view_paper":"https://pith.science/paper/RMEJCKMK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.01038&json=true","fetch_graph":"https://pith.science/api/pith-number/RMEJCKMKAES2TSKRR3IZJE2EUK/graph.json","fetch_events":"https://pith.science/api/pith-number/RMEJCKMKAES2TSKRR3IZJE2EUK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RMEJCKMKAES2TSKRR3IZJE2EUK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RMEJCKMKAES2TSKRR3IZJE2EUK/action/storage_attestation","attest_author":"https://pith.science/pith/RMEJCKMKAES2TSKRR3IZJE2EUK/action/author_attestation","sign_citation":"https://pith.science/pith/RMEJCKMKAES2TSKRR3IZJE2EUK/action/citation_signature","submit_replication":"https://pith.science/pith/RMEJCKMKAES2TSKRR3IZJE2EUK/action/replication_record"}},"created_at":"2026-07-05T07:51:15.408928+00:00","updated_at":"2026-07-05T07:51:15.408928+00:00"}