\n<\/p>\n
Australia said \u200bon Thursday an OpenAI agent breached a government health data portal in June, gaining unauthorised access to files, in what could be the \u200cfirst known instance of an AI agent hacking a government website.<\/strong><\/p>\n The breach is one of the highest-profile incidents of AI agents accessing external systems outside the United States, coming on top of several recent breaches globally by rogue AI agents that have alarmed governments and companies.<\/p>\n Prime Minister Anthony Albanese said the OpenAI agent gained unauthorised access to the medical statistics portal of Medicare, Australia\u2019s \u200buniversal health insurance programme, while conducting research on public medical spending.<\/p>\n \u201cEvidence currently available is there is no broader compromise to the \u2026 network. Nonetheless, this situation \u200bis obviously unacceptable,\u201d Albanese told reporters on Wednesday in New York, where he is attending the UN General Assembly.<\/p>\n Investigations continue \u2060and Australia has voiced its \u201cextreme concern about this incident\u201d to OpenAI CEO Sam Altman, Albanese said, adding that he was deeply disappointed by the company\u2019s delay in \u200bnotifying the government. \u201cIt took until September 10 before there was any notification at all,\u201d Albanese said, adding that the investigation would also examine why government systems had failed \u200bto detect the breach in the first place.<\/p>\n He also warned that three other government health-related websites may have been impacted by the OpenAI agent\u2019s activity, but did not confirm that had occurred.<\/p>\n In a statement, OpenAI said its \u201creview found no evidence of patient records being accessed.\u201d<\/p>\n It added that it \u201cidentified activity involving several Australian government websites and services as our models attempted to look up \u200banswers \u2026 our models took actions we did not intend.\u201d<\/p>\n The AI agent breach adds to tensions between Australia and the largest US-owned technology companies. Canberra has already \u200bdrawn criticism from social media firms and Washington after introducing a world-first ban on social media for children under 16 and new rules that force tech firms to let users switch off algorithm-driven \u200ccontent on \u2060their feeds.<\/p>\n The Australian government has set up a task force to investigate the breach and check whether existing network security is adequate for preventing similar incidents.<\/p>\n The breach was announced the same day the world\u2019s leading AI companies warned the United Nations Security Council of the risks AI posed to humanity, appealing for governments to work together to manage the increasingly powerful technology.<\/p>\n Australia has faced a series of hacking attempts on corporations and government-linked firms over the past four years.<\/p>\n\u2018AI MODELS ATTEMPTED TO LOOK UP ANSWERS\u2019<\/strong><\/h2>\n