AI-powered computer worms herald ‘new era’ of cybersecurity threats

Computer worms operating in tandem with free AI chatbots are a “new class of cyberthreat”, security experts have warned.

Worms are a type of malware that self-replicate and spread across computer networks without requiring human interaction, unlike viruses, which require unsuspecting users to open an infected file.

They can copy themselves rapidly, clogging system memory and network bandwidth to overload or crash systems.

This makes anti-virus software crucial to protect against them.

One example is the WannaCry worm, which was responsible for a global ransomware attack in 2017. It targeted computers running Microsoft Windows by encrypting data and demanded ransom payments in bitcoin.

Now, scientists have shown for the first time that publicly accessible large language AI models can be used to power worms that adapt their strategy as they spread from one device to the next. In comparison to more complex, proprietary AI systems such as ChatGPT, such publicly accessible models are open and more easily adaptable – making them useful for researchers but also easier to adapt and use for harm.

“The worm parasitically uses compromised machines to run open-access large language models (LLMs) to sustain its reasoning, or extend its reach for further attacks,” researchers warn in a yet-to-be peer-reviewed study posted in arXiv.

“Deployed on a network of machines spanning Linux, Windows, and IoT (Internet of Things) devices, the worm propagated by exploiting common, real-world corporate network vulnerabilities,” they wrote.

In the latest study, conducted at a secure digital lab walled off from the outside world, scientists simulated the capabilities of an AI-driven worm on dozens of interconnected devices, including laptops, printers and cameras.

“It was imperative for us to understand this threat in a controlled, academic setting before bad actors figured it out for themselves,” said Nicolas Papernot, one of the authors of the new study from the University of Toronto.

“The reason we are doing this research is to ensure the security of the digital ecosystem we all rely on – to keep people safe. This finding catapults us into a new era of cybersecurity,” Dr Papernot said.

A growing body of studies shows that AI models like OpenAI’s ChatGPT and Google’s Gemini can be tricked into losing their safety guardrails and manipulated to share harmful information.

Researchers showed that publicly accessible AI models could be used to engineer far more sophisticated threats, including ones that can scope out their targets and tailor attacks to take over a machine, before cloning itself onto the next one.

“Our results demonstrate that self-sustaining AI-driven cyber-threats are no longer theoretical. We must prepare for autonomous generative adversaries,” scientists wrote.

The Google Threat Intelligence Group has detected the first known instance of a threat actor using an AI-developed zero-day exploit in the wild. While the attackers planned a wide-scale strike, our proactive counter-discovery may have prevented that from happening. This finding…

Worms made using AI can adapt and gather information as it moves deeper into a network, with every breach revealing passwords and weak points that can unlock another machine, scientists warn.

“Hackers have typically had to prioritise the most high-value targets because time and computing resources were limited. But now, once a worm is launched, the cost would drop to nearly zero,” Dr Papernot said.

“Every device connected to the internet – laptops, cameras, smart thermostats and everything else – becomes a potential target, if not for the data it holds, then as a foothold to attack more valuable targets,” he said.

Such AI-powered worms could gain internet access and scan and exploit warning notices about newly discovered vulnerabilities, outpacing the software patches meant to stop them, researchers warn.

“In an interconnected world, no system is immune to this threat. Sharing these findings is the first step in galvanising researchers, industry leaders and policymakers to take action – and quickly,” the cybersecurity expert said.

“We can no longer afford to hit ‘ignore’ on software updates. Every door you close is one less way in, so it’s worth taking a few minutes to reboot,” Dr Papernot warned.

Hate AI support? Over 70% of Americans would like the option to speak to a human

Anthropic scrambles to reverse AI ban after Amazon’s White House warning

Musk will be the first trillionaire – and it’s all science fiction

The kids using AI to accurately predict this year’s exam questions

Google must ‘improve transparency and fairness’ of search results, says CMA

Telegram fights back against India ban over exam leaks