SYDNEY, Sept 23 (Reuters) – Australia said on Wednesday that an AI agent developed by OpenAI breached a government health data portal in June, gaining unauthorised access to public and non-public files, in what could be the first known instance of an AI agent hacking a government website.
The breach marks one of the highest-profile incidents of AI agents accessing external systems outside the United States, and could fuel concerns about developers’ ability to contain the technology.
Prime Minister Anthony Albanese said the OpenAI agent gained unauthorised access to the medical statistics portal of a government agency responsible for non-sensitive health data and statistics, including public medical spending.
“Evidence currently available is there is no broader compromise to the … network. Nonetheless, this situation is obviously unacceptable,” Albanese said during a media briefing in New York, where he is attending the UN General Assembly.
He said investigations continue and Australia has expressed its “extreme concern about this incident” directly to OpenAI Chief Executive Sam Altman.
The incident comes after OpenAI and Anthropic, in separate submissions to a parliamentary inquiry this month, urged Australia to reconsider a ban preventing them from using the country’s creative content to train their models.
In a statement, OpenAI said it “identified activity involving several Australian government websites and services as our models attempted to look up answers … our models took actions we did not intend.”
“Our review found no evidence of patient records being accessed. The information accessed included aggregate health statistics and internal file names,” it said.
Australian Defence Minister Richard Marles said that though the hack occurred in June, the government became aware of the incident “a couple of weeks ago.”
The breach is one of several recent incidents in which OpenAI has disclosed hacks or unauthorised activity involving its AI agents well after they occurred — in some cases because the activity was only detected belatedly, and in others because the company initially elected not to disclose it.
A separate high-profile incident, a mid-July intrusion into open-source AI repository Hugging Face, was only detected about a week after it took place, according to time lines released by OpenAI and independent investigators. This helped ignite a global conversation about the risks posed by increasingly powerful AI models.
Rivals Anthropic, Google’s Gemini, and Meta have also disclosed incidents of their agents accessing external systems.
Some of America’s top AI executives, including Altman, have called for a slowdown of AI development, citing, among other things, the threat of devastating cyber attacks by out-of-control agents.
(Reporting by Renju Jose in Sydney, Chris Thomas in Mexico City, Gnaneshwar Rajan in Bengaluru, Raphael Satter; Editing by Maju Samuel and Jonathan Spicer )
Comments