List your company

Jailbreaking Attack Detection on Role-Playing Jailbreaking Prompts

71AccMCAReGA
3.420.9538.556.05Jun 2, 2025

Evaluation results

MethodLinks
ReGATarget LLM=llama2025.067171
ReGATarget LLM=vicuna2025.066944
ReGATarget LLM=qwen2025.066241
ReGATarget LLM=mistral2025.065136
ReGATarget LLM=baichuan2025.063030
ReGATarget LLM=koala2025.0666