OpenAI agent breached Australian government website, PM says

An OpenAI artificial intelligence agent gained unauthorised access to an Australian government website in June, accessing public and non-public files from a Medicare statistics portal in what cybersecurity experts have described as the first known autonomous AI breach of a government system.

Prime Minister Anthony Albanese said the incident involved the Medicare Statistics Reporting Service portal, a public-facing site administered by Services Australia that contains aggregated, non-sensitive Medicare statistics, including spending data. No personal information is believed to have been accessed, but a forensic investigation is underway.

Albanese said he had a “very frank discussion” with OpenAI CEO Sam Altman, criticizing the company for taking “too long” to notify Australian authorities. He said there would be “legal consequences” if the investigation determined that police involvement was warranted.

OpenAI said it discovered the breach in August while reviewing “misaligned model activity” during an internal evaluation. It notified Services Australia by email on Sept. 10, nearly three months after the incident. The agency escalated the matter to Australia's cybersecurity authorities on Sept. 15, after verifying the notification.

Albanese said he expressed Australia's “extreme concern about this incident” and his “disappointment” over both the delay and “the nature of the way” OpenAI disclosed it. He said Altman acknowledged there were “issues with protocols” at the company.

OpenAI said its models had been attempting to find answers and statistics about Australia during an internal evaluation.

“In the course of that, our models took actions we did not intend,” the company said, adding that the information accessed included “aggregate health statistics and internal file names.” OpenAI said its review found no evidence that patient records had been accessed.

Three other Australian government websites were involved in the AI models' activity: the Australian Institute of Health and Welfare, the New South Wales Bureau of Crime Statistics and Research, and the Victorian Department of Health. Officials said those interactions involved publicly available information and were considered normal.

Cybersecurity experts told the BBC that the incident should serve as a warning to regulators as autonomous AI agents become more widely available.

Dr Hammond Pearce of the University of New South Wales Institute for Cyber Security said similar incidents were likely to increase.

“I expect that these kinds of attacks will keep occurring,” he said, adding that they would likely “grow in severity and in frequency”.

“I do hope that this incident does start ringing alarm bells in governments around the world.”

By Tamilla Hasanova