[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"$f-Nqf7oXezz4cBJBr20MLp2xK2m7YB_LXg3PSuGVXF9o":3},{"locale":4,"topic":5,"relatedTrends":116},"fr",{"topic":6,"slug":7,"canonicalSlug":8,"topicAliases":9,"nicheKey":21,"nicheName":22,"nicheNameEn":22,"nicheIcon":23,"country":24,"countries":25,"agentKey":26,"score":27,"type":28,"isFresh":29,"isPublic":30,"detectedAt":31,"sources":32,"evidence":108,"article":112},"University of Toronto free open-weight AI worm compromising networks","open-weight-llm-enabling-adaptive-ai-worm-attacks","university-of-toronto-free-open-weight-ai-worm-compromising-networks",[10,11,12,13,14,15,16,17,18,19,20],"Free open-weight LLM enabling an adaptive AI worm attack","Free open-weight LLM used to power adaptive AI worm","Free open-weight LLM enables adaptive AI worm compromising systems","Free open-weight LLM powering adaptive AI worm exploit","Free open-weight AI worm compromising simulated networks at Infosecurity","Open-weight agentic AI worm compromising simulated networks (73.8%)","Free open-weight AI worm compromising simulated systems at Infosecurity","Open-weight LLM enabling adaptive AI worm attacks","University of Toronto demo: free LLM powering adaptive worm","Free open-weight LLM powering adaptive AI worm","Free open-weight LLM enabling adaptive AI worm in security demo","ai-engineering","AI Engineering & LLM Ops","⚙️","US",[24],"ai-engineering-US",100,"spiking",false,true,"2026-06-05T01:28:32.879Z",[33,39,45,50,55,60,65,70,75,80,85,90,94,99,103],{"title":34,"url":35,"domain":36,"snippet":37,"content":38},"Agentic AI Security Alarm at Infosecurity Europe: Free LLM Now Powers Adaptive Worm","https:\u002F\u002Fwww.techtimes.com\u002Farticles\u002F317784\u002F20260604\u002Fagentic-ai-security-alarm-infosecurity-europe-free-llm-now-powers-adaptive-worm.htm","techtimes.com","Researchers demonstrated at Infosecurity Europe that a free open-weight agentic AI worm can compromise 73.8% of a simulated environment, raising urgent security concerns.","*   \n*   \n*   \n\nBy\n\nPublished: Jun 04 2026, 13:33 PM EDT \n\n!\n\nInfosecurity Europe\n\nThe final bell rang Thursday at Infosecurity Europe 2026 — the 31st edition of Europe's largest annual cybersecurity gathering — as the industry's most uncomfortable thesis moved from theoretical to demonstrated. Across three days at ExCeL London, more than 13,000 security professionals and 380 exhibitors debated how to defend against autonomous AI systems while, in the same week, a University of Toronto research team published proof that a self-propagating AI worm can be built today using free, publicly available large language models, no specialist tradecraft, and no proprietary compute budget — and that it can compromise nearly three-quartes of a simulated enterprise network in seven days.\n\nThat convergence — a live research demonstration, a White House AI cybersecurity executive order signed Tuesday, CISA advisories on active attacks against fuel infrastructure, and a critical Cisco vulnerability with public exploit code — gave Infosecurity Europe 2026 an operational edge rarely felt at industry gatherings. The sessions were not describing a future threat environment. They were responding to one already in motion.\n\nNo topic commanded more floor time across the three-day event than agentic AI, and the industry's\n\n[Content truncated...]",{"title":40,"url":41,"domain":42,"snippet":43,"content":44},"Autonomous AI-driven worm can reason its way through corporate networks","https:\u002F\u002Fwww.helpnetsecurity.com\u002F2026\u002F06\u002F03\u002Fautonomous-ai-worm-prototype\u002F","helpnetsecurity.com","Researchers at the University of Toronto, the Vector Institute, and the University of Cambridge have built and tested a proof-of-concept AI-driven worm that...",null,{"title":46,"url":47,"domain":48,"snippet":49,"content":44},"Nobody needs Mythos or 0-days to build a chaos-causing computer worm – free open source models work just fine","https:\u002F\u002Fwww.theregister.com\u002Fresearch\u002F2026\u002F06\u002F04\u002Ffree-ai-model-powers-self-spreading-worm-in-enterprise-test-network\u002F5250918","theregister.com","'Attackers can now cheaply operationalize known vulnerabilities at scale,' boffins tell The Reg.",{"title":51,"url":52,"domain":53,"snippet":54,"content":44},"Open-Weight LLM Enables Autonomous AI Worm","https:\u002F\u002Fwww.opensourceforu.com\u002F2026\u002F06\u002Fopen-weight-llm-enables-autonomous-ai-worm\u002F","opensourceforu.com","Researchers at the University of Toronto's CleverHans Lab have developed a self-replicating AI worm powered by an open-weight LLM, demonstrating how...",{"title":56,"url":57,"domain":58,"snippet":59,"content":44},"AI Accelerates Vulnerability Exploitation, Shortens Remediation Windows","https:\u002F\u002Fletsdatascience.com\u002Fnews\u002Fai-accelerates-vulnerability-exploitation-shortens-remediati-5a5b284d","letsdatascience.com","Security reporting highlights a fast-growing risk: attackers are using artificial intelligence to compress the vulnerability lifecycle from discovery to...",{"title":61,"url":62,"domain":63,"snippet":64,"content":44},"Researchers build self-replicating AI worm with BYO LLM","https:\u002F\u002Fwww.itnews.com.au\u002Fnews\u002Fresearchers-build-self-replicating-ai-worm-with-byo-llm-626409","itnews.com.au","A team of researchers at the University of Toronto in Canada has assembled a self-replicating malware - a worm - that is able to reason its way through...",{"title":66,"url":67,"domain":68,"snippet":69,"content":44},"Open Source AI Models Power New Chaos Causing Computer Worms","https:\u002F\u002Fstreamlinefeed.co.ke\u002Fnews\u002Fopen-source-ai-models-power-new-chaos-causing-computer-worms","streamlinefeed.co.ke","University of Toronto researchers reveal that free artificial intelligence models can create highly destructive, self-spreading computer worms in networks.",{"title":71,"url":72,"domain":73,"snippet":74,"content":44},"AI worm adapts across networks, turning any online device into potential target","https:\u002F\u002Ftechxplore.com\u002Fnews\u002F2026-06-ai-worm-networks-online-device.html","techxplore.com","A team of researchers at the University of Toronto has discovered a new class of cyberthreat that gives hackers more power and reach at far less cost.",{"title":76,"url":77,"domain":78,"snippet":79,"content":44},"New AI Cyber Worm Thinks Up Its Own Attacks To Infect Computers","https:\u002F\u002Fhothardware.com\u002Fnews\u002Fnew-ai-cyber-worm-thinks-up-its-own-attacks-to-infect-computers","hothardware.com","A proof of concept shows that a worm developed by an open AI model running on a single GPU can adapt to spread and exploit vulnerabilities across networks.",{"title":81,"url":82,"domain":83,"snippet":84,"content":44},"AI Powered Malware Worm Prototype Adapts Attacks Across Hosts","https:\u002F\u002Fwinbuzzer.com\u002F2026\u002F06\u002F03\u002Ftoronto-ai-worm-prototype-tests-adaptive-malware-risk-xcxwbn\u002F","winbuzzer.com","Researchers built a contained AI powered malware worm that adapts attacks across lab hosts, exposing how local open-weight models complicate malware...",{"title":86,"url":87,"domain":88,"snippet":89,"content":44},"This AI-Driven Computer Worm Can Adapt to Attack Different Devices","https:\u002F\u002Fau.pcmag.com\u002Fai\u002F118070\u002Fthis-ai-driven-computer-worm-can-adapt-to-attack-different-devices","au.pcmag.com","Researchers at the University of Toronto say their project highlights the risk of open-weight AI models being weaponized. The worm was able to spread over a...",{"title":91,"url":92,"domain":58,"snippet":93,"content":44},"AI-Powers Worm Exploits Stolen Compute to Infect Mixed Devices","https:\u002F\u002Fletsdatascience.com\u002Fnews\u002Fai-powers-worm-exploits-stolen-compute-to-infect-mixed-devic-69aba5d6","Per GBHackers, researchers published a proof-of-concept AI-driven worm that uses an embedded open-weight `LLM` running locally on compromised GPUs to...",{"title":95,"url":96,"domain":97,"snippet":98,"content":44},"AI-Powered Worm Leverages Stolen Compute to Target Linux, Windows, and IoT Devices","https:\u002F\u002Fgbhackers.com\u002Fai-powered-worm-leverages-stolen-compute-devices\u002F","gbhackers.com","How large language models (LLMs) can autonomously compromise mixed networks of Linux, Windows, and IoT devices.",{"title":34,"url":100,"domain":36,"snippet":101,"content":102},"http:\u002F\u002Fwww.techtimes.com\u002Farticles\u002F317784\u002F20260604\u002Fagentic-ai-security-alarm-infosecurity-europe-free-llm-now-powers-adaptive-worm.htm","Researchers demonstrated a free open-weight LLM powering an adaptive worm that compromised 73.8% of a simulated environment, raising agentic AI security alarms.","*   \n*   \n*   \n\nBy\n\nPublished: Jun 04 2026, 13:33 PM EDT \n\n!\n\nInfosecurity Europe\n\nThe final bell rang Thursday at Infosecurity Europe 2026 — the 31st edition of Europe's largest annual cybersecurity gathering — as the industry's most uncomfortable thesis moved from theoretical to demonstrated. Across three days at ExCeL London, more than 13,000 security professionals and 380 exhibitors debated how to defend against autonomous AI systems while, in the same week, a University of Toronto research team published proof that a self-propagating AI worm can be built today using free, publicly available large language models, no specialist tradecraft, and no proprietary compute budget — and that it can compromise nearly three-quartes of a simulated enterprise network in seven days.\n\nThat convergence — a live research demonstration, a White House AI cybersecurity executive order signed Tuesday, CISA advisories on active attacks against fuel infrastructure, and a critical Cisco vulnerability with public exploit code — gave Infosecurity Europe 2026 an operational edge rarely felt at industry gatherings. The sessions were not describing a future threat environment. They were responding to one already in motion.\n\nNo topic commanded more floor time across the three-day event than agentic AI, and the industry's re\n\n[Content truncated...]",{"title":104,"url":105,"domain":106,"snippet":107,"content":44},"A new AI-powered computer worm could prove to be the stuff of cybersecurity nightmares","https:\u002F\u002Ffortune.com\u002F2026\u002F06\u002F03\u002Fa-new-ai-powered-computer-worm-could-prove-to-be-the-stuff-of-cybersecurity-nightmares\u002F","fortune.com","University of Toronto researchers built a worm powered by open-weight AI that adapts to its targets. Experts say it changes the math on cybersecurity...",{"mentionsLast7Days":109,"mentionsLast30Days":109,"firstSeen":31,"lastSeen":110,"relatedEntities":111},4,"2026-06-07T01:10:32.408Z",[100,105,72,52,77,82],{"slug":113,"title":114,"matchScore":115},"open-weight-llms-and-adaptive-ai-worms-how-local-models-turn-malware-into-autonomous-attackers","Open-weight LLMs and Adaptive AI Worms: How Local Models Turn Malware into Autonomous Attackers",1,[117,120,123,126,129,130],{"topic":118,"slug":119,"score":27,"type":28,"country":24,"nicheIcon":23},"AI engineering intelligence platforms for measuring engineering outcomes","ai-engineering-intelligence-platforms-for-measuring-engineering-outcomes",{"topic":121,"slug":122,"score":27,"type":28,"country":24,"nicheIcon":23},"Use of commercial models to scale and automate cyber attacks","use-of-commercial-models-to-scale-and-automate-cyber-attacks",{"topic":124,"slug":125,"score":27,"type":28,"country":24,"nicheIcon":23},"AI engineering intelligence platforms measuring impact on engineering outcomes","ai-engineering-intelligence-platforms-measuring-impact-on-engineering-outcomes",{"topic":127,"slug":128,"score":27,"type":28,"country":24,"nicheIcon":23},"Six-layer AI agents stack between LLMs and production agents","six-layer-ai-agents-stack-between-llms-and-production-agents",{"topic":127,"slug":128,"score":27,"type":28,"country":24,"nicheIcon":23},{"topic":131,"slug":132,"score":27,"type":28,"country":24,"nicheIcon":23},"Six-layer AI agents stack between LLM and production agents","six-layer-ai-agents-stack-between-llm-and-production-agents"]