prompt-hacking-classifier
PublicA flexible and portable solution that uses a single robust prompt and customized hyperparameters to classify user messages as either malicious or safe, helping to prevent jailbreaking and manipulation of chatbots and other LLM-based solutions.
Creat:2024-06-13T16:51:20
Update:2024-10-17T04:45:00
6
Stars
0
Stars Increase