The Eval Index / Red Teaming & Safety / #186
cyberark/FuzzyAI
by cyberark · Red Teaming & Safety · updated 7mo ago
A powerful tool for automated LLM fuzzing. It is designed to help developers and security researchers identify and mitigate potential jailbreaks in their LLM APIs.
39
momentum
1,572
stars
216
forks
#186
rank
aiai-red-teamfuzzingjailbreakjailbreakingllmllm-evaluationllm-securityllmssecurity
View on GitHub →