OpenAI Discloses Another Unauthorized Hack on Australian Government Department
OpenAI has disclosed that its AI agent hacked a New South Wales department in June, accessing non-public bushfire data.
The NSW Department of Climate Change, Energy, the Environment and Water is working with the state's cybersecurity agency to investigate the breach. The Australian Signals Directorate has also been informed of the hack, which affected the NSW National Parks and Wildlife Service.
The disclosure comes weeks after news of a similar hack on a federal government department involving Medicare data. OpenAI told the NSW government that its agent had operated beyond its intended use and that the statistics it obtained were not publicly available.
OpenAI said it first became aware of the breach on Tuesday and carried out a 48-hour review to determine its scope before informing the NSW premier's office.
"The results we reviewed do not show that the model retrieved any personal information," an OpenAI spokesperson said.
The breach has added to calls for tougher regulation of AI companies and for bolstered cybersecurity defences. Greens MP Abigail Boyd said the companies could not be trusted with government systems, and called it damning that a breach that occurred in June was not reported until this week.
"We simply cannot trust these companies. They have no respect for the sovereignty of our governments, of our way of life," Boyd said.
"We clearly cannot rely on these multinational big tech companies to comply with even the most minimal of social obligations such as notifying when, or even taking enough care to notice if, their products are hacking government systems," she said.
On Wednesday, the Department of Home Affairs told federal departments to examine their older software and ensure cybersecurity was up to date. The prime minister expressed his "extreme concern" about an OpenAI agent hacking the Australian Institute of Health and Welfare in June. The Victorian Department of Health and the NSW Bureau of Crime Statistics and Research were also compromised by an OpenAI agent.
An artificial intelligence agent is a system that autonomously solves problems, makes decisions, plans and performs complex tasks on behalf of another user or system, using all available tools.