<p>University of Toronto researchers said they used open source technology to create an agentic AI worm that reasons and adapts — identifying each targeted device’s unique vulnerabilities and creating tailored attack strategies on the fly.</p>
<p>Traditional worms are one-trick ponies that self-replicate and spread across machines by exploiting a single, fixed security flaw or set of flaws. <a href=”https://www.techtarget.com/searchsecurity/definition/WannaCry-ransomware”>WannaCry</a>, for example, took advantage of the EternalBlue vulnerability in outdated versions of Windows’ Server Message Block protocol. In that case, the flaw’s ubiquity led to cataclysmic results — with WannaCry compromising around 10% of all internet-connected systems in the U.S. in less than a day — but organizations could readily defend themselves with patches.</p>
<p>In contrast, in a recently published <a href=”https://arxiv.org/html/2606.03811v1″>draft</a> of their findings, the Toronto researchers said they built a proof-of-concept (POC) AI worm that dynamically and autonomously identifies and exploits known security vulnerabilities by querying open-source large language models (LLMs). It is also self-sustaining, stealing compute resources from compromised machines to host the LLMs — making the marginal cost per new infection zero for an attacker and <a href=”https://www.techtarget.com/searchcio/feature/How-open-source-AI-drains-compute-budgets”>considerable for victims</a>.</p>
<p>The paper described the worm’s behavior in a simulated corporate environment with Linux, Windows and IoT devices, where it exploited <a href=”https://www.techtarget.com/searchsecurity/feature/How-to-fix-the-top-5-cybersecurity-vulnerabilities”>common network vulnerabilities</a> to rapidly spread. According to researchers, within seven days of fully autonomous operation, the worm had successfully exploited 73.8% of the isolated test network.</p>
<section class=”section main-article-chapter” data-menu-title=”How worried should CISOs be?”>
<h2 class=”section-title”><i class=”icon” data-icon=”1″></i>How worried should CISOs be?</h2>
<p>”We can comfortably presume that if someone acting as a defender in the infosec community has come up with this idea, then someone in the attacker world has also set such tooling in motion,” said Mike Wilkes, CISO at cybersecurity vendor Aikido Security. But while CISOs should take the news seriously, he added, they don’t need to panic.</p>
<blockquote class=”main-article-pullquote”>
<div class=”main-article-pullquote-inner”>
<figure>
We can comfortably presume that if someone acting as a defender in the infosec community has come up with this idea, then someone in the attacker world has also set such tooling in motion.
</figure>
<figcaption>
<strong>Mike Wilkes </strong>CISO, Aikido Security
</figcaption>
<i class=”icon” data-icon=”z”></i>
</div>
</blockquote>
<p>Trevor Horwitz, CISO at cybersecurity vendor TrustNet, agreed, adding that AI worms are not a new category of risk. Rather, they represent an evolution of challenges CISOs already know and understand, such as automated malware, lateral movement, weak segmentation and poor identity controls.</p>
<p>There is also a vast difference between a secure lab environment and a real-world corporate network, Horwitz added, making it far from certain that we will see a similar AI worm in the wild soon.</p>
<p>”Real enterprise networks are messy,” he said. “They have inconsistent configurations, legacy systems, security tooling, partial visibility and a lot of operational friction. That makes real-world propagation harder than a lab demo.”</p>
<p>In a more likely near-term scenario, according to Horwitz, attackers use AI to improve pieces of the attack chain: reconnaissance, exploit selection, <a href=”https://www.techtarget.com/searchsecurity/tip/Generative-AI-is-making-phishing-attacks-more-dangerous”>phishing</a>, credential abuse and <a href=”https://www.techtarget.com/searchsecurity/tip/How-to-prevent-and-detect-lateral-movement-attacks”>lateral movement</a>.</p>
<p>”The significance of this research isn’t the worm itself — it’s the emergence of more autonomous attacks,” agreed Martin Reynolds, field CTO at DevSecOps vendor Harness. “AI gives attackers greater speed, scale and adaptability, often against the same vulnerabilities and misconfigurations security teams have faced for years.”</p>
</section>
<section class=”section main-article-chapter” data-menu-title=”How to defend against AI worms”>
<h2 class=”section-title”><i class=”icon” data-icon=”1″></i>How to defend against AI worms</h2>
&
[…]
Content was cut in order to protect the source.Please visit the source for the rest of the article.
Read the original article: