Artificial intelligence experts are cautioning the public to enhance their cybersecurity measures by using robust passwords and promptly updating software on their devices to counter the threat of “AI-driven computer worms.” These advanced cyber threats are capable of launching customized attacks on devices, draining processing power and stealing information as they seek out new targets.
Recently, a team from the University of Toronto, led by Nicolas Papernot, the Canadian Institute for Advanced Research AI chair, revealed that publicly available AI models can be utilized to create a worm that can adapt its attack techniques on the go as it spreads across internet-connected devices such as laptops, printers, and cameras.
The research, carried out in partnership with the Vector Institute, was shared with national science, security, and defense entities before its publication. Papernot, an associate professor at U of T specializing in computer engineering and computer science, emphasized the importance of not neglecting software updates and regularly changing passwords during a panel discussion at the university.
Unlike traditional computer viruses, worms can autonomously spread from one machine to another without human intervention. The AI worm developed by the U of T researchers gathers data as it moves between devices, exploiting weaknesses and passwords to infiltrate new machines. In uncontrolled scenarios, such worms could access the internet, learning about newly identified vulnerabilities and outmaneuvering software patches meant to thwart them.
Papernot highlighted that these AI-driven worms are capable of crafting tailored attack strategies for each victim device, making them more challenging to combat compared to previous cyber threats. The cost-effectiveness of developing and deploying these worms poses a significant cybersecurity risk, enabling hackers to target a larger number of victims.
Recent incidents, such as AI agents breaching the Hugging Face platform and the development of a “zero-click” worm for WeChat calls, underscore the escalating concerns surrounding AI security. Papernot’s research findings emphasize the urgent need to strengthen cybersecurity practices across Canada, especially in critical infrastructure sectors like power grids, healthcare facilities, and schools, which are increasingly vulnerable to cyber threats.
A survey conducted by the Communications Security Establishment (CSE) revealed that while a significant percentage of Canadians regularly update their software and use complex passwords, there is room for improvement in adopting unique passwords and enhancing overall cybersecurity practices.
As the landscape of cyber threats evolves, Papernot’s warnings serve as a reminder of the critical importance of maintaining robust cybersecurity measures to safeguard against the growing menace of AI-driven cyber attacks.