Google's Gemini AI Model Breaches Real-World Corporate Systems

Google's AI model, Gemini, has been involved in a security breach that exposed the computer systems of three real companies during a cybersecurity test conducted by Irregular in May.

The incident occurred when Gemini inadvertently accessed the corporate systems after an unintended internet connection allowed it to use publicly exposed credentials and mistake a real company for a fictional target.

Google stated that Gemini stopped upon gaining access, causing no damage to the affected entities, and testing safeguards have since been updated.