- Albanese said in New York that an OpenAI agent accessed both public and non-public files on the Medicare Statistics Reporting Service portal on 18 June, and that no personal information is believed to have been taken.
- OpenAI said it found the activity in August during a review of misaligned model activity and emailed Services Australia on 10 September, a delay Albanese called way too long after speaking with CEO Sam Altman.
- A taskforce led by the Prime Minister’s department will review the incident, with the Australian Signals Directorate investigating and urgent advice sought on whether offences occurred and whether to refer the matter to the Australian Federal Police.
Prime Minister Anthony Albanese told reporters in New York on Wednesday, U.S. time, that an OpenAI agent gained unauthorised access to the Medicare Statistics Reporting Service portal on 18 June and accessed both public and non-public files, prompting a forensic investigation aided by the Australian Signals Directorate and a taskforce review.
The portal, administered by Services Australia, holds non-sensitive Medicare information such as spending statistics, Albanese said. “No personal information is believed to have been accessed at this stage, but investigations are ongoing”, he stated, adding that evidence shows no broader compromise to the Services Australia network.
On 18 June, OpenAI’s research team used an internal model to conduct internet-based research into public medicine spending, Albanese said, and the AI agent found a way around those blocks, leading to “unauthorised access into some other areas”.
Read more: ZetaChain Tokenholders Vote to Shut Down Layer 1 and Move to Solana
Three Months to Notify
OpenAI said it was not aware of the activity until August during an ongoing review of OpenAI misaligned model activity and emailed Services Australia on 10 September through a public inbox.
Services Australia read the email on 11 September and reported it to the directorate on 15 September, and Government Services Minister Katy Gallagher was told on 17 September.
Albanese said he spoke with OpenAI CEO Sam Altman to express Australia’s extreme concern about this incident and disappointment that it took the company way too long to inform the Government, calling the notification’s form unacceptable.
OpenAI spokesperson Drew Pusateri said the company’s models took actions we did not intend during an internal evaluation. The review “found no evidence of patient records being accessed”, he said, and the information accessed included aggregate health statistics and internal file names.
The taskforce, led by the Department of the Prime Minister and Cabinet, will “determine whether existing processes are appropriate to respond to AI-related cyber incidents”, Albanese said.
The government will refer the incident to Parliament’s Joint Select Committee on Artificial Intelligence and seek urgent advice on whether any offences have occurred and whether this should be referred to the Australian Federal Police, and the findings will feed the AI standards legislation Canberra is developing with the states.
Acting Prime Minister Richard Marles called it a “very serious incident” with a “relatively minor” impact. University of Queensland associate professor of AI governance Michael Noetel said the breach shows government infrastructure is not strong enough to protect against current AI models, a warning security researchers have also made about AI accelerating hacks.
Read more: Grayscale’s Zcash ETF Announces 3-for-1 Share Split as ZEC Surges 2,800%
Be the first to comment