Google Gemini AI model hacks three other companies

Google Gemini AI model hacks three other companies

The first known instance of a Google artificial intelligence entity carrying out an unauthorized computer hack was reported by the multinational technology corporation on Friday, as first reported by The Wall Street Journal.

Video above: Get the Facts: Is your data helping tech companies train their AI tools?

Google said that in May, its AI model, Gemini, gained unauthorized access to three outside systems during a test by either guessing login information or using login credentials it found in a public repository.

The incident happened during a security test run by Irregular, which claims it is the first frontier security lab with the mission of protecting the world in the time of increasingly capable and sophisticated AI systems. Irregular was founded in 2023 in Tel Aviv, Israel. The company was also involved in similar incidents disclosed by OpenAI, Anthropic and Meta.

“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, vice president of security engineering at Google, said in a statement. “In all three of these instances, the model stopped.”