[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"$fkNiaovC1bdrrIbaGiN_9re3eJbsbCbJDf99KeszWlWg":3},{"article":4,"iocs":47,"watch_terms":55,"solutions":56,"lesson":142},{"id":5,"title":6,"slug":7,"summary":8,"ai_summary":9,"brief":10,"url":11,"image_url":12,"published_at":13,"ingested_at":14,"relevance_score":15,"entities":16,"category_id":31,"category":32,"article_tags":36},"fddab941-136e-4c71-9c99-618238e2b8d1","Researchers Build Self-Replicating AI Worm That Operates Entirely on Local, Open-Weight Models","researchers-build-self-replicating-ai-worm-that-operates-entirely-on-local-open--b533fe","University of Toronto researchers have built and tested a proof-of-concept AI-driven computer worm that uses a locally hosted open-weight large language model to reason its way through a network, generate tailored attack strategies for each target it encounters, and replicate itself, all without human intervention and without touching a commercial AI service. The preprint, posted to arXiv on","Researchers from University of Toronto's CleverHans Lab built a proof-of-concept AI worm that uses locally hosted open-weight language models to reason through networks, generate tailored exploits at runtime, and self-replicate without external API dependencies. In 15 isolated tests on a 33-host network, the worm identified an average of 31.3 vulnerabilities, compromised 23.1 hosts, and propagated to 20.4 hosts (62% of the network) over seven days with no prior network knowledge. The worm demonstrated the critical vulnerability of patch-based defenses by ingesting public security advisories to exploit vulnerabilities unknown to its training data.","University of Toronto researchers demonstrated a self-replicating AI worm using local open-weight LLMs to autonomously","https:\u002F\u002Fthehackernews.com\u002F2026\u002F06\u002Fresearchers-build-self-replicating-ai.html","https:\u002F\u002Fblogger.googleusercontent.com\u002Fimg\u002Fb\u002FR29vZ2xl\u002FAVvXsEg2H1xd7_K6KgUGsDu0E9YGBOLVgXF4DX0rDhf_pUhDRujatedeTJFwy0e_JxsMGGpQB80HOn4wTXRSxCB2DrxNo0nHYVUJC2ehyphenhyphenum_Cyjg-5bVXOIuGahdDFIIa9NBleTGfYDXQuqf005BOME3HAXVxVQw1OXNJNZwpZ4Tgke2qUK2TITR0qFMgaAH8Mf9\u002Fs1600\u002Fworm.gif","2026-06-09T11:59:03+00:00","2026-06-09T14:00:29.444088+00:00",9,[17,20,22,24,27,29],{"name":18,"type":19},"University of Toronto","vendor",{"name":21,"type":19},"Vector Institute",{"name":23,"type":19},"ServiceNow",{"name":25,"type":26},"Open-weight LLM","technology",{"name":28,"type":26},"SambaCry",{"name":30,"type":26},"Dirty Pipe","839da5c1-3c34-47e2-9499-f7201640e3ac",{"id":31,"icon":33,"name":34,"slug":35},null,"AI Security","ai-security",[37,42],{"category":38},{"id":39,"icon":33,"name":40,"slug":41},"89f78b1c-3503-45a1-9fc7-e23d2ce1c6d5","Malware","malware",{"category":43},{"id":44,"icon":33,"name":45,"slug":46},"e7b231c8-5f79-4465-8d38-1ef13aea5a14","Threat Intelligence","threat-intelligence",[48,52],{"type":49,"value":50,"context":51},"cve","CVE-2026-39987","Vulnerability disclosed after model training; successfully exploited by the worm at runtime",{"type":41,"value":53,"context":54},"AI Worm (PoC - CleverHans Lab)","Self-replicating worm using local LLM for autonomous exploit generation",[18,21,23],{"controls":57,"vendors":141},[58,86,112],{"slug":59,"name":60,"problem":61,"products":62},"patch-management","Automated patch management","Known holes get closed in days, not months.",[63,71,79],{"vendor_slug":64,"vendor_name":65,"vendor_logo":66,"product_slug":67,"product_name":68,"url":69,"description":70},"manageengine","ManageEngine","\u002Fvendor-logos\u002Fmanageengine.png","patch-manager-plus","ManageEngine Patch Manager Plus","https:\u002F\u002Fwww.manageengine.com\u002Fpatch-management\u002F","Patch management for operating systems and third-party applications, on premises or in the cloud.",{"vendor_slug":72,"vendor_name":73,"vendor_logo":74,"product_slug":75,"product_name":76,"url":77,"description":78},"microsoft","Microsoft","\u002Fvendor-logos\u002Fmicrosoft.png","intune","Microsoft Intune","https:\u002F\u002Fwww.microsoft.com\u002Fen-us\u002Fsecurity\u002Fbusiness\u002Fmicrosoft-intune","Device management for Windows, macOS, iOS and Android, including update rings and compliance policies.",{"vendor_slug":80,"vendor_name":81,"vendor_logo":82,"product_slug":59,"product_name":83,"url":84,"description":85},"qualys","Qualys","\u002Fvendor-logos\u002Fqualys.png","Qualys Patch Management","https:\u002F\u002Fwww.qualys.com\u002Fapps\u002Fpatch-management\u002F","Patch deployment for operating systems and third-party applications, linked to vulnerability findings.",{"slug":87,"name":88,"problem":89,"products":90},"endpoint-detection-response","Endpoint detection and response (EDR and XDR)","Malware and hands-on-keyboard attackers on laptops and servers get spotted and stopped.",[91,99,104],{"vendor_slug":92,"vendor_name":93,"vendor_logo":94,"product_slug":95,"product_name":96,"url":97,"description":98},"elastic","Elastic","\u002Fvendor-logos\u002Felastic.png","elastic-security","Elastic Security","https:\u002F\u002Fwww.elastic.co\u002Fsecurity","SIEM and endpoint security built on Elasticsearch, with open detection rules.",{"vendor_slug":72,"vendor_name":73,"vendor_logo":74,"product_slug":100,"product_name":101,"url":102,"description":103},"defender-for-endpoint","Microsoft Defender for Endpoint","https:\u002F\u002Fwww.microsoft.com\u002Fen-us\u002Fsecurity\u002Fbusiness\u002Fendpoint-security\u002Fmicrosoft-defender-endpoint","Endpoint detection and response for Windows, macOS, Linux and mobile devices.",{"vendor_slug":105,"vendor_name":106,"vendor_logo":107,"product_slug":108,"product_name":109,"url":110,"description":111},"sophos","Sophos","\u002Fvendor-logos\u002Fsophos.png","sophos-endpoint","Sophos Endpoint","https:\u002F\u002Fwww.sophos.com\u002Fen-us\u002Fproducts\u002Fendpoint-security","Endpoint protection with Intercept X anti-ransomware technology and EDR.",{"slug":113,"name":114,"problem":115,"products":116},"network-segmentation","Network segmentation and microsegmentation","One compromised machine can no longer reach everything else.",[117,125,133],{"vendor_slug":118,"vendor_name":119,"vendor_logo":120,"product_slug":121,"product_name":122,"url":123,"description":124},"illumio","Illumio","\u002Fvendor-logos\u002Fillumio.png","illumio-segmentation","Illumio Segmentation","https:\u002F\u002Fwww.illumio.com\u002Fillumio-segmentation","Maps traffic between workloads and enforces segmentation across data centre, cloud and endpoints.",{"vendor_slug":126,"vendor_name":127,"vendor_logo":128,"product_slug":129,"product_name":130,"url":131,"description":132},"threatlocker","ThreatLocker","\u002Fvendor-logos\u002Fthreatlocker.png","zero-trust-endpoint-firewall","Zero Trust Endpoint Firewall","https:\u002F\u002Fwww.threatlocker.com\u002Fcapabilities\u002Fzero-trust-endpoint-firewall","Centrally managed host firewall with device-level and dynamic access rules, to limit which machines can talk to each other.",{"vendor_slug":134,"vendor_name":135,"vendor_logo":136,"product_slug":137,"product_name":138,"url":139,"description":140},"akamai","Akamai","\u002Fvendor-logos\u002Fakamai.png","guardicore-segmentation","Akamai Guardicore Segmentation","https:\u002F\u002Fwww.akamai.com\u002Fproducts\u002Fakamai-guardicore-segmentation","Software-based microsegmentation with traffic visibility.",[],{"slug":143,"title":144,"body":145,"framework_refs":146,"framework_notes":154},"ai-worm-exploits-local-models-to-autonomously-compromise-networks","AI Worm Exploits Local Models to Autonomously Compromise Networks","Researchers demonstrated that AI worms can operate entirely on local language models, automatically discovering and exploiting vulnerabilities across networks without human intervention or external dependencies. The worm successfully compromised 62% of a test network by ingesting public security advisories to exploit previously unknown vulnerabilities, highlighting the inadequacy of traditional patch-based defenses against AI-powered threats. This represents a paradigm shift where attackers can leverage AI to autonomously reason through complex network environments and generate tailored exploits in real-time. Organizations must evolve beyond reactive patching to proactive vulnerability management and robust network isolation strategies.",[147,148,149,150,151,152,153],"CIS Control 7","CIS Control 12","NIST SC-7","NIST SI-2","NIST IR-4","MITRE ATT&CK T1210","ISO 27001 A.12.6.1",{}]