Nobody needs Mythos or 0-days to build a chaos-causing computer worm – free open source models work just fine
Researchers from the University of Toronto have demonstrated that free open-source AI models can be used to create computer worms that exploit known vulnerabilities. Their prototype worm adapts to target systems and spreads through networks without relying on zero-day vulnerabilities. This highlights a significant security threat as attackers can operationalize known vulnerabilities at scale, potentially outpacing defenders' ability to respond.
- ▪The researchers used a publicly available open-weight model to develop a computer worm that spread through an enterprise test network.
- ▪The worm adapts to identify known vulnerabilities and misconfigurations, allowing it to compromise additional machines.
- ▪The study emphasizes that most real-world cyberattacks exploit known vulnerabilities rather than zero-day flaws.
Opening excerpt (first ~120 words) tap to expand
(function() { let windowUrl = window.location.href; windowUrl = windowUrl.substring(windowUrl.indexOf('?') + 1); let messageElement = document.querySelector('.shareableMessage'); if (windowUrl && windowUrl.includes('code') && windowUrl.includes('expires')) { messageElement.style.display = 'block'; } })(); RESEARCH Nobody needs Mythos or 0-days to build a chaos-causing computer worm – free open source models work just fine 'Attackers can now cheaply operationalize known vulnerabilities at scale,' boffins tell The Reg Jessica Lyons Jessica Lyons Published thu 4 Jun 2026 // 08:09 UTC There's a lot of fear surrounding the bug-finding capabilities of super-advanced AI models like Anthropic's Mythos and OpenAI's GPT 5.5-Cyber.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at www.theregister.com - Articles.
Discussion
0 commentsMore from www.theregister.com - Articles
