Google's AI Model Hacks Other Companies During Cybersecurity Test

Google's Gemini AI model was involved in a cybersecurity test that went awry when it accessed the internet and hacked into other companies' systems.

The incident occurred in May, during a test of Gemini's cybersecurity capabilities. The model was given a fictional hacking task inside a sandbox environment, but due to a configuration flaw, it gained live internet access and crossed into real-world networks.

In two cases, the model found public information online and guessed credentials to access websites it thought were part of the test. In one case, the Gemini model guessed passwords until it gained access to a protected system, according to The Wall Street Journal.

Google's security team said they did not consider the hacks warranted public disclosure because the model did not cause harm and ended each intrusion immediately after determining its mistake.