1.11 Gone in 60 seconds: BEAST AI model attack needs just a minute of GPU time to breach LLM guardails

News


<< back

Gone in 60 seconds: BEAST AI model attack needs just a minute of GPU time to breach LLM guardails
Date: 2024-02-29 [theregister.co.uk]

Scientists reveal automated adversarial prompt generation too powered Nvidia visualization accelerator

Computer scientists from the University of Maryland have developed an efficient way to generate adversarial attack phrases that elicit harmful responses from large language models (LLMs).
READ THE FULL NEWS >>

×