+34
A team of researchers have shown how a self-replicating AI agent can take over a computer network at almost no cost.
A team of researchers have shown how a self-replicating AI agent can take over a computer network at almost no cost. It’s a nightmare scenario that’s long haunted the imaginations of cybersecurity experts: computer malware that spreads autonomously from device to device, learning as it goes and exploiting different vulnerabilities along the way.
Now, researchers have demonstrated that such a “worm” can in fact be built today, with publicly available AI models, and at a disconcertingly low cost.published Tuesday by a team from the University of Toronto, the University of Cambridge, and elsewhere outlines “a fundamentally new threat: a worm that generates tailored attack strategies to each target it encounters,” according to the researchers. The paper described how the team deployed an AI agent to act as a worm in a controlled, isolated network composed of Linux, Windows, and IoT devices and “with common corporate network vulnerabilities,” such as reused passwords.
The agent was powered by an unnamed open source LLM. Unlike a traditional computer virus, which needs a human to be duped into, say, opening a file infected with malware, worms can infect devices entirely on their own by exploiting security vulnerabilities and replicating into copies of itself along the way. They spread via a shared digital connection, such as a wifi network, to find other vulnerable devices it can infect.
And they precede the LLM boom: back in 2017, the aptly-titled WannaCry worm, allegedly, spread to hundreds of thousands of devices spread across more than 150 countries. The malware held the infected devices hostage until their owners paid a Bitcoin ransom. The WannaCry fiasco and other worm incidents underscored the vulnerabilities that come with a globally interconnected digital ecosystem. But they: WannaCry exploited a single security vulnerability, which was promptly patched up, eliminating any further spread.
The University of Toronto team’s experimental worm, in contrast, is able to dynamically detect security flaws that are unique to each particular device it infects, thereby using a variety of tactics to propagate through a network. It also parasitically feeds off devices’ computing power, a problem which, as the researchers point out in their paper, is made more dire by the fact that those devices are now being built to support computationally expensive LLMs.
Smartphones and laptops built for AI, in other words, are an abundant feeding ground for this kind of worm.
“As consumer devices increasingly support LLM inference, the reasoning resources available to such adversaries grow accordingly,” the researchers write in aexplaining their work. That “means every machine connected to the internet is a potential target—if not for the data it holds, then as a launching pad for the next attack.
” The AI worm moves slower than traditional worms, since at each point along its path of propagation it needs to meticulously probe for potential points-of-entry into the next device; it took about five days to infect half of the devices in the experimental network, the researchers noted. But that timeframe will compress as devices get more efficient at inference and as AI models improve in their ability to detect security flaws, the researchers warn.
The paper arrives at an anxious moment for the cybersecurity sector, which is already trying to come to grips with the possible ramifications of powerful new AI systems that are able to discover and exploit security vulnerabilities at an unprecedented scale. In April, Anthropic announced it had developed a model called.
The goal of that effort is to give the cybersecurity community the opportunity to figure out how such a powerful system can be used to strengthen defense more than it empowers the offense. OpenAI launched its own model trained to detect cybersecurity vulnerabilities, called GPT-5.4-Cyber, a few weeks after Mythos launched, and has likewise only shared it with a limited group of early testers.
In a similar spirit, the University of Toronto researchers said they published the paper in hopes of waking the global cybersecurity community up to the new threat. They also noted that they consulted with government and scientific bodies beforehand to assess how to best make their findings available without empowering hackers. Along with the identity of the open source model that was used to power the worm, other key methodological details were omitted from the published paper.
“We shared enough information to make the threat credible enough for scientific scrutiny without providing a blueprint that would enable misuse,” they wrote. Big Tech Still Has No Clue What to Do With AI Gadgets Microsoft wants you to wear an AI badge and the rest of the field doesn't seem to be faring much better. A New Declaration Warns AI Could Threaten the Foundations of Mathematics
Scratch the next story
Please follow us on Google to support usUnited States Latest News, United States Headlines
Similar News: You can also read news stories similar to this one that we have collected from other news sources.
First Look at Spider‑Man: Brand New Day Reveals New Villain Tombstone and Expands MCU ConnectionsMarvel and Sony unveil the initial artwork for Spider‑Man: Brand New Day, introducing the formidable antagonist Tombstone, confirming the return of key cast members, and hinting at a crossover with Jon Bernthal's Punisher as the sequel sets a darker tone for Peter Parker's future.
Read more »
Fan-Made New Austin Mod for Red Dead Redemption 2 Gets Stunning New TrailerA new trailer for Project New Austin, an ambitious fan-made mod for Red Dead Redemption 2, showcases extensive updates to the New Austin region, aiming to recapture the essence of the original game. The mod adds new interiors and improvements, with fans praising its polished, official-like quality.
Read more »
New Sequel Novel 'Kiki and the New Magic' Set to Continue Studio Ghibli's Beloved StoryNearly four decades after the original novel's release and the subsequent Studio Ghibli film adaptation, a new sequel novel titled 'Kiki and the New Magic' is set to be released this August. The story follows Kiki a year after she started her delivery service, now facing the challenges of fame and new perilous tasks, testing her friendships and her magical resolve. The book is written by the original author Eiko Kadono with illustrations by Yuta Onoda and translation by Emily Balistrieri. There is no official confirmation yet on whether this sequel will be adapted into a film by Studio Ghibli.
Read more »
How to Sell Now: Multi-BrandWholesale is not disappearing, but its role in luxury has fundamentally changed.
Read more »