Researchers Show How to Use One LLM to Jailbreak Another
"Tree of Attacks With Pruning" is the latest in a growing string of methods for eliciting unintended behavior from a large language model.
Source: darkreading.com
Stay updated with breaking news from Prompt Automatic Iterative Refinement. Get real-time updates on events, politics, business, and more. Visit us for reliable news and exclusive interviews.
"Tree of Attacks With Pruning" is the latest in a growing string of methods for eliciting unintended behavior from a large language model.
This process is repeated until PAIR either discovers a jailbreak or exhausts a predetermined number of attempts.