List your company

Style Manipulation Attack on DeepSeek-R1-Distill

1.997ScoreBITE
-0.079880.459310.99851.53769May 24, 2026

Evaluation results

MethodLinks
BITEOptimization Steps=25, Attack Type=Black-box2026.051.997
JudgeDeceiverOptimization Steps=25, Attack Type=White-box2026.050
JudgeDeceiverOptimization Steps=100, Attack Type=White-box2026.050
JudgeDeceiverOptimization Steps=200, Attack Type=White-box2026.050
JudgeDeceiverOptimization Steps=300, Attack Type=White-box2026.050
JudgeDeceiverOptimization Steps=600, Attack Type=White-box2026.050