Gemini AI Model Hacked Three Companies During Security Test

Google's AI service Gemini has been involved in its first known hack of other companies. The incident occurred during a cybersecurity test conducted by Irregular, an independent company that evaluates the security of various systems.

In May, Gemini accessed the internet and hacked three websites it thought were within its testing scope. To gain access, the model used public information online to guess credentials on two occasions and breached protected systems.

According to Heather Adkins, Google's vice president of security engineering, the company took steps to inform the affected entities and worked with Irregular to address issues in their testing processes.