{"version":"1.0","type":"card","id":"71195774-537c-48b8-8f37-3329aeabe037","url":"https://stacklist.com/card/71195774-537c-48b8-8f37-3329aeabe037","title":"Autonomous AI-driven worm can reason its way through corporate networks - Help Net Security","source_url":"https://www.helpnetsecurity.com/2026/06/03/autonomous-ai-worm-prototype/","note":"Researchers have built an AI-driven worm that does not operate on a fixed list of exploits and does not rely on commercial AI platforms.","image":{"url":"https://ucarecdn.com/af66241d-6512-4a82-9b58-f4213beddf5f/","alt":"Autonomous AI-driven worm can reason its way through corporate networks - Help Net Security","width":1456,"height":816},"stack":{"id":"5d8cc977-ef65-41d4-b39f-7509ea94663a","title":"spod","url":"https://stacklist.com/stack/5d8cc977-ef65-41d4-b39f-7509ea94663a"},"created_at":"2026-06-24T12:07:51.689Z","updated_at":null,"aco":{"summary":"Researchers from University of Toronto, Vector Institute, and University of Cambridge developed an AI-driven worm that uses a large language model to autonomously reason through corporate networks, identify vulnerabilities, and create exploitation strategies on the fly. The prototype successfully identified and exploited vulnerabilities across diverse systems by running locally on compromised hardware, demonstrating the emerging threat of AI-powered autonomous cyberattacks.","tags":["ai-worm","cybersecurity","autonomous-attack","llm","vulnerability-exploitation"],"key_entities":[{"name":"Zeljka Zorz","type":"person","confidence":0.95},{"name":"University of Toronto","type":"organization","confidence":0.95},{"name":"Vector Institute","type":"organization","confidence":0.95},{"name":"University of Cambridge","type":"organization","confidence":0.95},{"name":"Help Net Security","type":"organization","confidence":0.95},{"name":"CleverHans Lab","type":"organization","confidence":0.9},{"name":"large language model","type":"technology","confidence":0.95},{"name":"AI-driven worm","type":"technology","confidence":0.95},{"name":"autonomous reasoning","type":"concept","confidence":0.9},{"name":"vulnerability exploitation","type":"concept","confidence":0.95},{"name":"Toronto","type":"location","confidence":0.9},{"name":"Cambridge","type":"location","confidence":0.9},{"name":"AI worm research study","type":"event","confidence":0.85}],"classification":"analysis","language":"en","confidence":0.85,"provenance":{"model":"claude-haiku-4-5","tool":"@stacklist/be@0.1.0","confidence":0.85,"timestamp":"2026-06-24T12:08:02.960Z"},"token_counts":{"approximate":1497,"cl100k":1123},"content_hash":"sha256:2d8cf9cfc9fa40eb4f71ff50df9e2e73d943333b9da05d35dfd541c0ba9383ee","acp_version":"0.2","body_available":true,"body_tokens":1497,"visibility":"public","agent_accessible":true,"status":"final"},"_links":{"self":"/api/public/card/71195774-537c-48b8-8f37-3329aeabe037.json","html":"https://stacklist.com/card/71195774-537c-48b8-8f37-3329aeabe037","md":"/api/public/card/71195774-537c-48b8-8f37-3329aeabe037.md","stack_json":"/api/public/stack/5d8cc977-ef65-41d4-b39f-7509ea94663a.json"}}