AI-powered hacking has exploded into industrial-scale threat, Google says

In just three months, AI-powered hacking has gone from a nascent problem to an industrial-scale threat, according to a report from Google.

The findings from Google’s threat intelligence group add to an intensifying, global discussion about how the newest AI models are extremely adept at coding – and becoming extremely powerful tools for exploiting vulnerabilities in a broad array of software systems.

It finds that criminal groups, as well as state-linked actors from China, North Korea and Russia, appear to be widely using commercial models – including Gemini, Claude and tools from OpenAI – to refine and scale up attacks.

“There’s a misconception that the AI vulnerability race is imminent. The reality is that it’s already begun,” said John Hultquist, the group’s chief analyst.

“Threat actors are using AI to boost the speed, scale, and sophistication of their attacks. It enables them to test their operations, persist against targets, build better malware and make many other improvements.”

Last month, the AI company Anthropic declined to release one of its newest models, Mythos, after asserting that it had extremely powerful capabilities and posed a threat to governments, financial institutions and the world generally if it fell into the wrong hands.

Specifically, Anthropic said Mythos had found zero-day vulnerabilities in “every major operating system and every major web browser” – the term for a flaw in a product previously unknown to its developers.

The company said these discoveries necessitated “substantial coordinated defensive action across the industry”.

Google’s report found, however, that a criminal group recently was on the verge of leveraging a zero-day vulnerability to conduct a “mass exploitation” campaign – and that this group appeared to be using an AI large language model (LLM) that was not Mythos.

The report also found that groups were “experimenting” with OpenClaw, an AI tool that went viral in February for offering its users the ability to hand over large chunks of their lives to an AI agent with no guardrails and an unfortunate tendency to mass-delete email inboxes.

Steven Murdoch, a professor of security engineering at University College London, said AI tool could help the defensive side in cybersecurity – as well as the hackers.

“That’s why I’m not panicking. In general we have reached a stage where the old way of discovering bugs is gone, and it will now all be LLM-assisted. It will take a little while before the consequences of this get shaken out,” he said.

However, if AI is helping ambitious hackers to reach their productivity goals, doubts remain as to whether it is bolstering the broader economy.

The Ada Lovelace Institute (ALI), an independent AI research body, has cautioned against assumptions of a multibillion-pound public sector productivity boost from AI. The UK government has estimated a £45bn gain in savings and productivity benefits from public sector investment in digital tools and AI.

In a report published on Monday, the ALI said most studies of AI-related increases in productivity referred to time savings or cost reductions, but did not look at outcomes such as better services or improved worker-wellbeing.

Other problematic aspects of such research include: whether projections of AI-related efficiency in a workplace really succeed in the real world; headline figures obscuring varying results for using AI in different tasks; and failing to account for the impact on public sector employment and service delivery.

“The productivity estimates shaping major government decisions about AI sometimes rest on untested assumptions and rely on methodologies whose limitations are not always appreciated by those using figures in the wild,” said the ALI report.

“The result is a gap between the confidence with which productivity claims are presented and the strength of the evidence behind them.”

The report’s recommendations include: encouraging future studies to reflect uncertainty over the impact of the technology; ensuring government departments measure the impact of AI programmes “from the start”; and supporting longer-term studies that measure productivity gains over years rather than weeks.