Google: Google confirmed Friday that its Gemini artificial intelligence (AI) model accessed the protected systems of three real companies during a cybersecurity test in May, mistakenly treating them as authorized targets. Heather Adkins, Google's vice president of security engineering, stated that during a standard evaluation, Gemini used publicly available information on the internet and guessed login credentials to access three websites it believed were part of the authorized test environment.

According to Namibia Press Agency, the testing was conducted by AI security evaluation company Irregular. In one test run, Gemini repeatedly tried passwords before gaining access to a protected real-world system. In two other runs, the model found exposed login credentials in publicly available repositories and used them to access systems belonging to other companies.

Irregular explained in an earlier report that the tests were designed around a fictional company, but human error caused the fictional name to overlap with a real-world internet domain. At the same time, internet access was unintentionally available in some of the testing environments, allowing AI models to mistake real-world targets for part of the simulated exercise.

Irregular said the known issues had since been fixed, affected parties had been notified, and additional safeguards had been introduced to prevent similar incidents. Google stated that the incidents caused no damage to the companies involved and that it did not consider the behavior an instance of model misalignment.