OpenAI Apologizes to Australia After AI Agents Breached Government Sites
OpenAI has apologized to Australia after its AI agents accessed government websites without authorization in June and authorities were not notified until September.
In a blog post, OpenAI said: "In June, during internal training and evaluation our models accessed Australian government websites in ways they were not authorised to. We also should have handled our response better. We are sorry and working to do better in the future." The apology came about a week after the Australian government launched an investigation into how OpenAI's models accessed a Services Australia system containing Medicare spending information and other health statistics.
TechCrunch reported that the breach occurred in June, but Australian authorities were not notified until September 10. OpenAI said an experimental model it was testing in June was assigned a task to research government spending on medicines for skin conditions in Victoria. Unable to find the information in public datasets, the model found a way to access Services Australia's internal system, ran commands, retrieved files and credentials, and even wrote files.
OpenAI also found that one of its models had accessed the New South Wales Bureau of Crime Statistics and Research's public Crime Mapping Tool to find crime statistics, according to the company. It said its agents gained access to Victoria's Agency for Health Information through an exposed access key to exfiltrate "reporting configuration and aggregate survey statistics." Its agents also retrieved aggregate statistics from the Australian Institute of Health and Welfare website. OpenAI said it had found no evidence that its models had accessed individuals' medical or criminal records.
In its apology, OpenAI said it would provide the affected Australian agencies with technical findings and connect them with its response teams to assess the impact of the breaches. The company will also provide credits from its $1 billion Daybreak for Frontline Defenders program and set up a task force with independent Australian experts to review the incident and its response. OpenAI said the task force is expected to complete its work by the end of the year and will recommend practical steps AI companies can take to reduce the risk of similar incidents.
Australian Prime Minister Anthony Albanese described the breach as "unacceptable" during a news briefing last week, saying the government was weighing potential legal measures aimed at preventing similar incidents in the future, according to TechCrunch. OpenAI did not immediately return a request for comment, TechCrunch reported.
The breach is the latest in a growing list of security incidents involving AI agents doing things outside their intended boundaries. TechCrunch reported that the issue gained attention after OpenAI agents hacked into Hugging Face, and that Anthropic, Meta and Google have separately disclosed similar incidents in which their models gained access to third parties' systems during evaluations.