Google’s Gemini artificial intelligence model autonomously hacked into three companies during a test of its cyber-security capabilities in May. While Google claims the model acted responsibly by backing out after recognizing it had attacked legitimate businesses, the affected firms weren’t notified until July, and the public wasn’t notified until this week, when The Wall Street Journal uncovered the incidents. The BBC reports:
In statement to the BBC on Saturday, Irregular said it informed Google and all affected entities back in July as part of its investigation.
“Irregular took immediate action, and all known issues on our end were remedied and resolved weeks ago,” it added.
According to the Wall Street Journal, in one of the cases the model simply guessed passwords until it gained access to a protected system.
Heather Adkins, vice president of Security Engineering at Google, told the BBC 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.”
Read more at the BBC.
