UK AI minister says AI cyber-attack like OpenAI Medicare breach ‘seems likely’

Narayan described the June incident as one in which an OpenAI agent — a computer program acting autonomously — infiltrated Medicare, Australia’s universal healthcare system. He said the agent’s task was “benign” because it searched for information about public spending on medicines, but it nonetheless went after data it was not authorised to have. The Australian government has said that no personal medical records are known to have been accessed, and there is no evidence of wider compromise, he added.

“It concerns me,” Narayan said. “It seems likely, if not inevitable, that our own cyber defences will be breached.”

Narayan spoke before a parliamentary hearing on AI safety on Tuesday. Senior figures from OpenAI and Anthropic will be among those giving evidence to MPs on the business, innovation, science and trade committee. They will be joined by Henry de Zoete, head of the UK’s AI Security Institute.

Narayan confirmed that the institute would gain access to advanced AI models before they were released, after the White House had reportedly placed restrictions on their availability. He said AI scientists at the institute were now conducting rigorous evaluations of the latest generations of models, including Google’s Gemini, to identify risks early and test robust safeguards to help keep people safe.

The minister added that leading AI companies must “listen” to warnings of safety risks posed by their technology and not release models if they carried a serious threat. “And to the companies developing the world’s most powerful AI systems, my message is: Listen when your scientists warn of severe dangers. Investigate unexpected behaviours. And if you can’t adequately control the risks, do not release the system,” he said. “I want the labs to be honest.”

Narayan said the UK would “play its part” in coordinating an international response to AI safety by making the technology a “central focus” of Britain’s G20 presidency next year. “We know that these challenges cannot be addressed by a single country alone, but by virtue of our capability, by virtue of the foundations of our trust, Britain will play its part,” he said.

Editor's Summary UK AI minister Kanishka Narayan said an AI-driven cyber-attack on UK defences is likely, if not inevitable, citing a June incident in which an OpenAI agent infiltrated Australia’s Medicare system. He said security minister Dan Jarvis would lead a government programme against cyber-attacks including AI, and confirmed the UK AI Security Institute would evaluate advanced models before release. The remarks came before a parliamentary hearing on AI safety with OpenAI, Anthropic, and UK officials.