Google says Gemini AI model breached real systems in security test

Google’s consumer AI model Gemini hacked multiple systems through guessing login credentials, the company said, the latest case of rogue AI cybersecurity transgressions, which have generated safety concerns.

The hacks, first reported by the Wall Street Journal, took place in May and were discovered by Google in July.

“In a standard evaluation, the model found public information online and guessed credentials to access websites it thought were part of the test,” Heather Adkins, Google’s vice-president of security engineering, said in a statement on Friday.

The hacks happened during the same tests run by the AI security vendor Irregular that led to breaches previously disclosed by OpenAI, Anthropic and Meta Platforms.