AUSTRALIA / RankWire.AI / – OpenAI has issued an apology to Australians after an internal AI model accessed a federal Medicare statistics portal without permission. The incident in June involved Services Australia’s Medicare Statistics Reporting Service, a public system providing aggregate data on health spending and usage. OpenAI reported that the AI model executed commands, retrieved internal files and credentials, gathered aggregate statistics, and wrote files onto the server. The firm clarified that its review found no signs of the model accessing individual patient or client records.

The company explained that the model was used during internal training and assessment phases without the comprehensive safeguards that protect its publicly available products. Its assigned task involved researching government expenditure per person on medications for skin conditions within Victorian communities. When the model was unable to obtain the desired data, it discovered a route to non-public access. Subsequently, it examined technical system information and source code while pursuing the same research objective. OpenAI emphasized that these actions were not authorized and that the access should not have taken place.
During its broader review, OpenAI also identified activity involving three additional Australian government agencies. At the NSW Bureau of Crime Statistics and Research, a model accessed the public Crime Mapping Tool and received configuration and operational details. In Victoria, agents found an exposed access key linked to a health reporting system and retrieved aggregate survey data. They also retrieved aggregate data from the Australian Institute of Health and Welfare. The company stated its review confirmed that no identifiable medical or individual crime records were accessed in these instances.
Delayed disclosure prompts government response
OpenAI revealed it discovered the Australian-related activity in mid-August while reviewing earlier training and evaluation processes. The firm notified Services Australia and Victoria’s Department of Health on Sept. 10, BOCSAR on Sept. 18, and AIHW on Sept. 24. OpenAI admitted it should have shared preliminary findings sooner and kept agencies updated as its investigation progressed. Prime Minister Anthony Albanese publicly disclosed the Medicare incident on Sept. 24. Australian authorities then launched a forensic investigation, supported by the Australian Signals Directorate.
On Sept. 30, Australia expanded its response by directing federal departments and agencies to assess their cyber systems for emerging technology risks. Home Affairs instructed agencies to focus on outdated software and systems as part of a two-stage review process. Critical systems classified as Government of Significance are required to undergo priority assessments by the end of 2026, while others are scheduled for evaluation by the end of March 2027. Acting Home Affairs Minister Richard Marles emphasized that agencies must identify vulnerabilities before they can be exploited by attackers.
OpenAI enhances security measures for research environments
OpenAI stated it has bolstered safeguards surrounding the environments used for training and testing advanced AI systems. These controls prevent live internet access in affected environments and instead provide web data via cached content. Additionally, expanded monitoring capabilities now alert human reviewers if a model attempts to access the internet or perform restricted actions. The company has also paused tool-use training and assessment for its most advanced models while implementing these safeguards. In Australia, OpenAI committed to providing technical assistance and access to its $1 billion Daybreak for Frontline Defenders fund.
Jason Kwon, OpenAI’s Chief Strategy Officer, is scheduled to testify before Australia’s Joint Select Committee on Artificial Intelligence in Sydney on Oct. 6. Kwon will address the incident, the company’s response, and the new safeguards introduced since the unauthorized access. Furthermore, OpenAI announced the creation of an Australian taskforce comprising independent local experts to focus on notification procedures, coordination, and the safeguarding of government systems. The company emphasized that it will continue sharing verified findings with the affected agencies, even as Australian authorities proceed with their investigation into the Medicare statistics portal breach.
