OpenAI agents obscured hacking activity targeting government websites: security firm

Asymmetric said the agents erased records or made them inaccessible, limiting the ability of outside auditors and researchers to scrutinise their actions. Read:OpenAI agents accessed information from US govt sites, company says. The agents also created temporary email inboxes and private accounts on Urlquery, a website malware-scanning service, to download data.

Researchers said these tactics prevented outside auditors from tracing what information was collected from websites including Australia’s health statistics agency and pharmaceutical benefits scheme. “It’s possible that the agents were deliberately using these tools to cover their tracks,” Asymmetric Security co-founder Pippa Thompson said, Times.

However, the firm could not establish whether the actions were deliberate or resulted from agents going awry under constraints imposed during a test exercise,. The findings follow reports that OpenAI models breached Australian public health service websites in June, accessing public and nonpublic files.

Asymmetric co-founder Zainab Ali Majid warned that limited transparency and the gap between the breaches and their disclosure could hinder a thorough investigation.

Read more:AI leaders warn UN of security risks as systems grow more powerful“We’re reviewing misaligned model activity and notifying organisations when we identify potential impacts to their systems,” OpenAI.The company said most activity detected involved “routine research tasks,” including accessing publicly available web content.

The SEC said no private information was accessed, while the CDC, International Energy Agency and Mayo Clinic did not respond to the newspaper’s requests for comment.