The Eval Index / Red Teaming & Safety / #256

dongdongunique/EvoSynth

by dongdongunique · Red Teaming & Safety · updated 7mo ago

EvoSynth is a SOTA automated LLM red-teaming framework that evolves executable, code-level jailbreak attack methods using multi-agent synthesis, evolutionary search, and self-correction.

22
momentum
60
stars
9
forks
#256
rank
ai-safetyautomated-red-teamingjailbreakllm-securitysota
View on GitHub →