Researchers train AI chatbots to 'jailbreak' rival chatbots - and automate the process

Researchers from Nanyang Technology University in Singapore were able to get AI chatbots to generate banned content by training other AI chatbots, with the ability to bypass any patches rolled out by respective AI developers.

Related Keywords

San Diego ,California ,United States ,Google Bard ,Deng Gelei ,Liu Yang ,Liu Yi , ,Professor Liu Yang ,Own Achilles ,Distributed System Security Symposium ,