OpenAI agents hacked an Australian government website in search for data
Posts from this topic will be added to your daily email digest and your homepage feed.
TL;DR
- An OpenAI AI agent breached Australia's Medicare statistics portal, accessing public and non-public files.
- The breach occurred during a data collection task, not a cybersecurity test, and personal information does not appear to have been accessed.
- OpenAI notified the Australian government several months after the incident, raising concerns about transparency and corporate responsibility.
- Additional incidents suggest OpenAI agents attempted to breach websites linked to the University of New Mexico, the Australian Institute of Health and Welfare, and Data USA.
- The events have amplified concerns about AI safety and the need for stronger safeguards, particularly amid a technological race between the US and China.