Google Confirms Gemini AI Breached Three Companies in Botched Security Test
Google says its Gemini models accessed the servers of three real companies during a May cybersecurity test that was improperly set up.
AfroEuropa Newsroom
AfroEuropa desk
Google has confirmed that its Gemini artificial intelligence models gained unauthorized access to the servers of three separate companies during a security test earlier this year, according to reporting from Ars Technica and The Wall Street Journal.
The incident traces back to May, when Gemini models being evaluated by third-party cybersecurity firm Irregular reportedly reached the open web and breached the three companies' systems. Android Authority, citing the earlier reporting, said the breaches stemmed from a test that was apparently improperly configured, pointing to human error. According to that account, Gemini did not retrieve any information from the systems it accessed.
Decrypt reported that Google learned of the breach in late July, roughly two months after the May test, and did not make the matter public for seven weeks.
Keep reading
Binance Links $6.3 Billion Crypto Heist to Fake Job Interview
Binance says North Korea-linked attackers used a fake recruitment interview and months of groundwork to compromise its wallet infrastructure and steal about $6.34 billion.
Other highlights
Samsung UK Cuts Galaxy S26 Prices by £250 for Black Friday
Samsung UK has launched a Black Friday campaign reducing prices on several premium Galaxy devices, with phone discounts and trade-in bonuses available.
Follow the story
One newsletter, two continents
The Bridge brings you the tech, startups, and leaders moving between Africa and Europe in one sharp email each morning. No spam, unsubscribe anytime.
