{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:EU6CNRYVVEQVX4XBHXRR6FTABE","short_pith_number":"pith:EU6CNRYV","schema_version":"1.0","canonical_sha256":"253c26c715a9215bf2e13de31f1660093c7a31b4f7163b0e177c8d801fe76445","source":{"kind":"arxiv","id":"2502.10931","version":2},"attestation_state":"computed","paper":{"title":"D-CIPHER: Dynamic Collaborative Intelligent Multi-Agent System with Planner and Heterogeneous Executors for Offensive Security","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.AI","authors_text":"Brendan Dolan-Gavitt, Farshad Khorrami, Haoran Xi, Kimberly Milner, Meet Udeshi, Minghao Shao, Muhammad Shafique, Nanda Rani, Prashanth Krishnamurthy, Ramesh Karri, Sandeep Kumar Shukla, Venkata Sai Charan Putrevu","submitted_at":"2025-02-15T23:43:18Z","abstract_excerpt":"Large Language Models (LLMs) have been used in cybersecurity such as autonomous security analysis or penetration testing. Capture the Flag (CTF) challenges serve as benchmarks to assess automated task-planning abilities of LLM agents for cybersecurity. Early attempts to apply LLMs for solving CTF challenges used single-agent systems, where feedback was restricted to a single reasoning-action loop. This approach was inadequate for complex CTF tasks. Inspired by real-world CTF competitions, where teams of experts collaborate, we introduce the D-CIPHER LLM multi-agent framework for collaborative "},"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":"2502.10931","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-15T23:43:18Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"d4242387603e50aa69a800bf50ffd7aa485b3efc033fd66ce95eedf0956f36e7","abstract_canon_sha256":"169701f6b43b497ae9702dc41e3b73cedfd9b5f882f8f0b205a569dbd52c4182"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:01:32.000225Z","signature_b64":"ti3L2oHI18MzEicB7omn5BZDYD55jLK5ZlmY0Ts2qTahEiQMySgu1aMudmKcYbUjF/kacvA/hFu/RDcfiEljAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"253c26c715a9215bf2e13de31f1660093c7a31b4f7163b0e177c8d801fe76445","last_reissued_at":"2026-07-05T11:01:31.999769Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:01:31.999769Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"D-CIPHER: Dynamic Collaborative Intelligent Multi-Agent System with Planner and Heterogeneous Executors for Offensive Security","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.AI","authors_text":"Brendan Dolan-Gavitt, Farshad Khorrami, Haoran Xi, Kimberly Milner, Meet Udeshi, Minghao Shao, Muhammad Shafique, Nanda Rani, Prashanth Krishnamurthy, Ramesh Karri, Sandeep Kumar Shukla, Venkata Sai Charan Putrevu","submitted_at":"2025-02-15T23:43:18Z","abstract_excerpt":"Large Language Models (LLMs) have been used in cybersecurity such as autonomous security analysis or penetration testing. Capture the Flag (CTF) challenges serve as benchmarks to assess automated task-planning abilities of LLM agents for cybersecurity. Early attempts to apply LLMs for solving CTF challenges used single-agent systems, where feedback was restricted to a single reasoning-action loop. This approach was inadequate for complex CTF tasks. Inspired by real-world CTF competitions, where teams of experts collaborate, we introduce the D-CIPHER LLM multi-agent framework for collaborative "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.10931","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/2502.10931/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":"2502.10931","created_at":"2026-07-05T11:01:31.999822+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.10931v2","created_at":"2026-07-05T11:01:31.999822+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.10931","created_at":"2026-07-05T11:01:31.999822+00:00"},{"alias_kind":"pith_short_12","alias_value":"EU6CNRYVVEQV","created_at":"2026-07-05T11:01:31.999822+00:00"},{"alias_kind":"pith_short_16","alias_value":"EU6CNRYVVEQVX4XB","created_at":"2026-07-05T11:01:31.999822+00:00"},{"alias_kind":"pith_short_8","alias_value":"EU6CNRYV","created_at":"2026-07-05T11:01:31.999822+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.26195","citing_title":"CyberEvolver: Structured Self-Evolution for Cybersecurity Agents On the Fly","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28146","citing_title":"Cybersecurity AI (CAI) Dataset","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29963","citing_title":"Honeyval: A Comprehensive Evaluation Framework for LLM-powered HTTP Honeypots","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15503","citing_title":"uGen: An Agentic Framework for Generating Microarchitectural Attack PoCs","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10597","citing_title":"CrackMeBench: Binary Reverse Engineering for Agents","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24184","citing_title":"Dynamic Cyber Ranges","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17948","citing_title":"RAVEN: Retrieval-Augmented Vulnerability Exploration Network for Memory Corruption Analysis in User Code and Binary Programs","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17159","citing_title":"Systematic Capability Benchmarking of Frontier Large Language Models for Offensive Cyber Tasks","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20389","citing_title":"CyberCertBench: Evaluating LLMs in Cybersecurity Certification Knowledge","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EU6CNRYVVEQVX4XBHXRR6FTABE","json":"https://pith.science/pith/EU6CNRYVVEQVX4XBHXRR6FTABE.json","graph_json":"https://pith.science/api/pith-number/EU6CNRYVVEQVX4XBHXRR6FTABE/graph.json","events_json":"https://pith.science/api/pith-number/EU6CNRYVVEQVX4XBHXRR6FTABE/events.json","paper":"https://pith.science/paper/EU6CNRYV"},"agent_actions":{"view_html":"https://pith.science/pith/EU6CNRYVVEQVX4XBHXRR6FTABE","download_json":"https://pith.science/pith/EU6CNRYVVEQVX4XBHXRR6FTABE.json","view_paper":"https://pith.science/paper/EU6CNRYV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.10931&json=true","fetch_graph":"https://pith.science/api/pith-number/EU6CNRYVVEQVX4XBHXRR6FTABE/graph.json","fetch_events":"https://pith.science/api/pith-number/EU6CNRYVVEQVX4XBHXRR6FTABE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EU6CNRYVVEQVX4XBHXRR6FTABE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EU6CNRYVVEQVX4XBHXRR6FTABE/action/storage_attestation","attest_author":"https://pith.science/pith/EU6CNRYVVEQVX4XBHXRR6FTABE/action/author_attestation","sign_citation":"https://pith.science/pith/EU6CNRYVVEQVX4XBHXRR6FTABE/action/citation_signature","submit_replication":"https://pith.science/pith/EU6CNRYVVEQVX4XBHXRR6FTABE/action/replication_record"}},"created_at":"2026-07-05T11:01:31.999822+00:00","updated_at":"2026-07-05T11:01:31.999822+00:00"}