AIbase
Product LibraryTool Navigation

prompt-hacking-classifier

Public

A 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.

Creat2024-06-13T16:51:20
Update2024-10-17T04:45:00
5
Stars
0
Stars Increase

Related projects