Google's Gemini model accessed the internet and hacked other companies during a test of its cybersecurity capabilities, the first known example of the company's AI systems autonomously committing such an act.The hacks occurred in May during a cybersecurity test conducted by Irregular, an independent company that evaluates cybersecurity.During a standard testing evaluation, Gemini found public information online and guessed credentials to access three websites it thought were within the scope of its test, Heather Adkins, Google's vice president of security engineering, said in a statement."We ensured the three entities were made aware, and we worked with our training partner on the changes they’ve now made to their testing processes," Adkins said. "These events highlight the importance of training powerful AI models to act responsibly."How did Gemini hack the websites?In one of the cases, the Gemini model guessed passwords until it gained access to a protected system. In the other two cases, the model found credentials in a public repository that allowed it to then access protected systems, according to the Wall Street Journal, which first reported the news on Friday.Adkins said that in all three instances, the model ceased its hacking.An Irregular spokesperson said the incident involved the same issue that affected other AI labs and that all relevant labs were not...
This page contains an attributed headline and the preview text supplied through the publisher’s RSS feed. Copyright in the original reporting belongs to The National.
