Jailbreaking AI-powered Robots (IMAGE)

University of Pennsylvania School of Engineering and Applied Science

Jailbreaking AI-powered Robots

Caption

The researchers demonstrated that malicious prompts can "jailbreak" AI-powered robots and cause them to perform unsafe actions.

Credit

Alexander Robey, Zachary Ravichandran, Vijay Kumar, Hamed Hassani, George J. Pappas

Usage Restrictions

Credit must be given to the creator. Adaptations must be shared under the same terms.

License

CC BY-SA

Disclaimer: AAAS and EurekAlert! are not responsible for the accuracy of news releases posted to EurekAlert! by contributing institutions or for the use of any information through the EurekAlert system.