The Eval Index / Red Teaming & Safety / #263
dongdongunique/EvoSynth
by dongdongunique · Red Teaming & Safety · updated 9mo 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.
21
momentum
61
stars
10
forks
#263
rank
ai-safetyautomated-red-teamingjailbreakllm-securitysota
View on GitHub →