Home Latest Australia NSW government launches cyber probe after rogue OpenAI model breaches National Parks...

NSW government launches cyber probe after rogue OpenAI model breaches National Parks system

4
0

Source : Perth Now news

Artificial intelligence leader Open AI said a rogue agent accessed a second NSW government website in June, with authorities only now made aware.

The NSW Premier’s Office released a statement on Friday night revealing OpenAI had advised the government of a “misalignment” involving a rogue AI agent which had accessed public data on a NSW government web application.

“An OpenAI model accessed a National Parks and Wildlife Service web application containing historical information and data on fires in NSW,” a government statement read.

“It’s understood the incident occurred in June 2026 and was validated by Open AI and reported through to NSW government on 1 October 2026.”

The statement advised current investigations had not identified any unauthorised access to personal information.

The NSW government has announced a second government website was accessed by Open AI software. NewsWire/ Gaye Gerard Credit: News Corp Australia

“The NSW Department of Climate Change, Energy, the Environment and Water (DCCEEW) is working with Cyber Security NSW and its technology service provider to investigate the matter and assess its impact,” it read.

It comes after Prime Minister Anthony Albanese revealed last week Open AI agents had accessed or tried to access data from four separate Australian government agencies in June, including Medicare data.

The agent also attempted to access the NSW Bureau of Crime Statistics and Research (BOCSAR), Victorian Department of Health, and the Australian Institute of Health and Welfare.

In the case of BOCSAR, the model asked for and accessed the site’s metadata but not crime records for individuals.

Open AI had sent a letter to a generic Services Australia email address to alert of the Medicare breach on September 10.

The company reportedly knew of the breach in August.

The breach did not involve the release of any personal information.

In a blog post titled “how we will do better for Australia”, OpenAI said its agent “accessed Australian government websites in ways they were not authorised to” during internal training and evaluation.

“We also should have handled our response better. We are sorry and working to do better in the future,” the post read.

On Tuesday, it was announced all Australian government agencies were directed to undertake a rapid review of “legacy systems”.

“AI is changing the environment in which we operate at extraordinary speed. Government systems need to keep up,” Acting Home Affairs Minister Richard Marles said of the direction.

“We can’t wait for an old system to fail before replacing it. We need to identify vulnerabilities and deal with them before they can be exploited.”