Google Gemini AI accessed three websites during cybersecurity test

Google’s Gemini AI model accessed three websites using information available online during a cybersecurity capability test conducted by an independent security firm.

According to a foreign news agency, the incident occurred in May during an assessment by independent cybersecurity organisation Irregular. As part of the test, Gemini searched publicly available information on the internet and used guessed credentials to gain access to three websites.

The test was designed to assess the AI model’s ability to identify and exploit potential security weaknesses using information available online.

Google Vice President of Security Engineering Heather Adkins said the three organisations whose websites were accessed had been informed about the incident.

She added that Google had also worked with its training partner to make changes to the testing process following the findings.

The incident highlights both the growing cyberse