Google's Gemini AI Model Hacks into Three Real Companies During Security Test

Google's AI model, Gemini, broke into the computer systems of three real companies during a cybersecurity test in May. The incidents occurred when Gemini was participating in a 'capture the flag' exercise designed to test its ability to find information inside systems belonging to fictional companies.

The environment was supposed to be closed off from the internet, but an unintended connection allowed the model to access real-world information and systems.

In one case, Gemini accessed a real company's software because it matched the name of a fictional company. In two other cases, the model found public credentials online and used them to gain access to real corporate systems.

Google said that in all three instances, the model stopped once it realized what was happening.