Artificial intelligence experts are cautioning individuals to utilize strong passwords and promptly update their software to defend against the emergence of AI-driven computer worms, a new type of cyber-threat capable of launching tailored attacks on devices, consuming processing power and data as they seek out new targets.

Recently, a team from the University of Toronto, led by Nicolas Papernot, Chair of the Canadian Institute for Advanced Research in AI, revealed that publicly accessible AI models could empower a worm that adapts its attack strategy dynamically as it spreads across internet-connected devices like laptops, printers, and cameras.

Collaborating with the Vector Institute, the researchers shared their findings with national science, security, and defense entities before releasing them. Papernot, an associate professor at the University of Toronto specializing in computer engineering and computer science, emphasized the importance of promptly updating software and regularly changing passwords to the public.

According to Papernot, the threat posed by AI-driven worms is a significant shift in cybersecurity risk. These worms, unlike traditional viruses, autonomously move from one device to another without human intervention, gathering information as they progress. This ability to gather data enables them to customize attack strategies for each victim device, making them more challenging to combat using conventional security measures.

Papernot highlighted the critical need for enhanced cybersecurity measures in light of these evolving threats, stressing the importance of multi-factor authentication, software updates, and proactive security practices. He also underscored the significance of organizations swiftly deploying software patches to mitigate potential risks.

The rise of AI-driven cyber threats has raised concerns among experts, with incidents such as the Hugging Face hack involving rogue AI agents and the development of a “zero-click” worm for WeChat calls on mobile operating systems. Papernot’s research underscores the urgency of addressing cybersecurity vulnerabilities and the imperative of strengthening defenses against increasingly sophisticated AI-driven attacks.

A survey conducted by the Communications Security Establishment (CSE) earlier this year revealed that while a majority of Canadians regularly update their software and use complex passwords, there is room for improvement in adopting unique passwords consistently. The survey highlights the need for ongoing efforts to enhance cybersecurity practices across various sectors, particularly critical infrastructure vulnerable to cyber threats.