{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:K2WDRMTWWRW5KVWLGEHBIVTUMB","short_pith_number":"pith:K2WDRMTW","schema_version":"1.0","canonical_sha256":"56ac38b276b46dd556cb310e1456746051ca3dd05e369a4b9e6249a4901e7bca","source":{"kind":"arxiv","id":"2505.12786","version":2},"attestation_state":"computed","paper":{"title":"Forewarned is Forearmed: A Survey on Large Language Model-based Agents in Autonomous Cyberattacks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.NI","authors_text":"Conghao Zhou, Dusit Niyato, Jiani Fan, Jiawen Kang, Kwok-Yan Lam, Minrui Xu, Shiwen Mao, Xinyu Huang, Xuemin (Sherman) Shen, Zhu Han","submitted_at":"2025-05-19T07:19:06Z","abstract_excerpt":"With the continuous evolution of Large Language Models (LLMs), LLM-based agents have advanced beyond passive chatbots to become autonomous cyber entities capable of performing complex tasks, including web browsing, malicious code and deceptive content generation, and decision-making. By significantly reducing the time, expertise, and resources, AI-assisted cyberattacks orchestrated by LLM-based agents have led to a phenomenon termed Cyber Threat Inflation, characterized by a significant reduction in attack costs and a tremendous increase in attack scale. To provide actionable defensive insight"},"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":"2505.12786","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.NI","submitted_at":"2025-05-19T07:19:06Z","cross_cats_sorted":[],"title_canon_sha256":"1d9daa56d40c915475ec9fe3fc3ccea87e603297b5d04ebcf2f8b0301f52312d","abstract_canon_sha256":"603ea12b174b8b1c04c65919f79da4af966d5528025ead3dc3e27da01d746f0f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:08.675268Z","signature_b64":"j8Dfpp23O/Bh2rds2U0SE9ntH7lAJ03DO+Qo97WkW3UZP6BgCgARfZMrRJcOYVGSI7vvpnQ+cDq/GbeI5xm5Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"56ac38b276b46dd556cb310e1456746051ca3dd05e369a4b9e6249a4901e7bca","last_reissued_at":"2026-07-05T11:10:08.674748Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:08.674748Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Forewarned is Forearmed: A Survey on Large Language Model-based Agents in Autonomous Cyberattacks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.NI","authors_text":"Conghao Zhou, Dusit Niyato, Jiani Fan, Jiawen Kang, Kwok-Yan Lam, Minrui Xu, Shiwen Mao, Xinyu Huang, Xuemin (Sherman) Shen, Zhu Han","submitted_at":"2025-05-19T07:19:06Z","abstract_excerpt":"With the continuous evolution of Large Language Models (LLMs), LLM-based agents have advanced beyond passive chatbots to become autonomous cyber entities capable of performing complex tasks, including web browsing, malicious code and deceptive content generation, and decision-making. By significantly reducing the time, expertise, and resources, AI-assisted cyberattacks orchestrated by LLM-based agents have led to a phenomenon termed Cyber Threat Inflation, characterized by a significant reduction in attack costs and a tremendous increase in attack scale. To provide actionable defensive insight"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12786","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/2505.12786/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":"2505.12786","created_at":"2026-07-05T11:10:08.674808+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.12786v2","created_at":"2026-07-05T11:10:08.674808+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12786","created_at":"2026-07-05T11:10:08.674808+00:00"},{"alias_kind":"pith_short_12","alias_value":"K2WDRMTWWRW5","created_at":"2026-07-05T11:10:08.674808+00:00"},{"alias_kind":"pith_short_16","alias_value":"K2WDRMTWWRW5KVWL","created_at":"2026-07-05T11:10:08.674808+00:00"},{"alias_kind":"pith_short_8","alias_value":"K2WDRMTW","created_at":"2026-07-05T11:10:08.674808+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01793","citing_title":"Safety Testing LLM Agents at Scale: From Risk Discovery to Evidence-Grounded Verification","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10749","citing_title":"Toward Secure LLM Agents: Threat Surfaces, Attacks, Defenses, and Evaluation","ref_index":214,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06486","citing_title":"Autonomous Adversary: Red-Teaming in the age of LLM","ref_index":7,"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":38,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04442","citing_title":"Explainable Autonomous Cyber Defense using Adversarial Multi-Agent Reinforcement Learning","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K2WDRMTWWRW5KVWLGEHBIVTUMB","json":"https://pith.science/pith/K2WDRMTWWRW5KVWLGEHBIVTUMB.json","graph_json":"https://pith.science/api/pith-number/K2WDRMTWWRW5KVWLGEHBIVTUMB/graph.json","events_json":"https://pith.science/api/pith-number/K2WDRMTWWRW5KVWLGEHBIVTUMB/events.json","paper":"https://pith.science/paper/K2WDRMTW"},"agent_actions":{"view_html":"https://pith.science/pith/K2WDRMTWWRW5KVWLGEHBIVTUMB","download_json":"https://pith.science/pith/K2WDRMTWWRW5KVWLGEHBIVTUMB.json","view_paper":"https://pith.science/paper/K2WDRMTW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.12786&json=true","fetch_graph":"https://pith.science/api/pith-number/K2WDRMTWWRW5KVWLGEHBIVTUMB/graph.json","fetch_events":"https://pith.science/api/pith-number/K2WDRMTWWRW5KVWLGEHBIVTUMB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K2WDRMTWWRW5KVWLGEHBIVTUMB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K2WDRMTWWRW5KVWLGEHBIVTUMB/action/storage_attestation","attest_author":"https://pith.science/pith/K2WDRMTWWRW5KVWLGEHBIVTUMB/action/author_attestation","sign_citation":"https://pith.science/pith/K2WDRMTWWRW5KVWLGEHBIVTUMB/action/citation_signature","submit_replication":"https://pith.science/pith/K2WDRMTWWRW5KVWLGEHBIVTUMB/action/replication_record"}},"created_at":"2026-07-05T11:10:08.674808+00:00","updated_at":"2026-07-05T11:10:08.674808+00:00"}