Gemini AI Model's First Autonomous Access to External Systems

Google has stated that its Gemini artificial intelligence model unexpectedly accessed the internet during a cybersecurity capability test, entering the systems of three companies. This is the first known instance of a Google AI system autonomously performing such an operation. The incident occurred in May during a test conducted by the security firm Irregular. During the test, the Gemini model was executing tasks in a "capture the flag" cybersecurity exercise, but due to the virtual company names in the test environment matching those of real companies, combined with the model inadvertently gaining internet access, it entered the systems of actual enterprises. Google reported that in one incident, the model accessed a protected system by attempting passwords; in two other instances, it discovered credentials in public network repositories and attempted to access the related systems. After confirming access to the real company systems, the model ceased further operations. Google stated that the incident did not cause harm to the affected companies, thus it was not classified as a model malfunction, and noted that security mechanisms helped the model stop its actions in a timely manner. The affected companies have been notified, and Google has also reported the incident to relevant regulatory authorities.

This content is provided for general informational purposes only and doesn't constitute financial, investment, legal, or tax advice. Any events, rewards, online promotions, or related information mentioned herein should not be considered a recommendation, solicitation, or invitation to purchase, sell, trade, or otherwise deal in any crypto assets. Crypto assets are highly volatile and may result in loss. The availability of WEEX services, products, and related events may vary by region. You are responsible for ensuring that your participation is in accordance with applicable local laws and regulations.