New York [US], September 24 (ANI): An OpenAI artificial intelligence agent hacked into an Australian government website and accessed non-public data, Australian Prime Minister Anthony Albanese said, in what seems to be the first known AI hack of a government system.
Albanese, during a press conference on the sidelines of the United Nations General Assembly (UNGA) on Wednesday, after speaking with OpenAI CEO Sam Altman, said that the incident involved Australia’s Medicare statistics portal and occurred in June.
According to Albanese, an OpenAI research team had initially been using an internal model for internet-based research into public medicine spending.
The AI agent encountered blocks while attempting to obtain information but subsequently found ways around them, leading to unauthorised access to other areas of the portal.
“On June 18, OpenAI’s research team used an internal model to conduct internet-based research into public medicine spending. So that’s how this began,” he said.
“After encountering repeated blocks, so there’s an AI agent looking for information, asking questions. There were blocks clearly which were coming back telling the AI agent, no. The AI agent found a way around those blocks. Didn’t accept no for an answer, if you like,” the Australian PM added.
“The model attempted alternate ways to obtain the info that it wanted and this led to unauthorised access into some other areas. It accessed public and non-public information within the portal and Services Australia also advises that in order to do this, it engaged in writing files as well to the internal server,” he further said.
Albanese said he had spoken with Altman to convey Australia’s “extreme concern” over the incident and his disappointment with the length of time taken by OpenAI to come forward.
The Prime Minister said the incident was particularly concerning because it demonstrated a risk that AI companies themselves had previously identified.
“Put simply, humans must remain in control,” he said.
Albanese also said a forensic investigation, with assistance from the Australian Signals Directorate, was underway to determine the full extent of the incident and whether other government systems were affected.
OpenAI spokesperson Drew Pusateri said the incident occurred in June and that the company became aware of the activity in August while conducting extensive checks into the actions of its AI models.
“During this review, we identified activity involving several Australian government websites and services as our models attempted to look up answers and available statistics for questions about Australia during an internal evaluation. In the course of that, our models took actions we did not intend,” Pusateri said, as per CNN.
According to Albanese, OpenAI did not notify Australian authorities until September, with the initial notification sent “to just the public mailbox”.
The Prime Minister said that he was only informed of the incident over the weekend.
The incident comes as governments and technology companies continue to discuss safeguards and oversight for increasingly capable AI systems.
Australia was among 22 countries that this month signed a joint statement calling for global oversight and guardrails for AI development.
OpenAI had also revealed earlier this year that a group of AI agents it had been testing had escaped their controls and secretly worked together to hack another technology company, Hugging Face.
The Australian incident is now under investigation, with authorities examining the extent of the access and whether other government systems were affected. (ANI)
Related reading
