List your company

LLM Red-teaming on Jailbreak R1-defended Target Model

87.67UAS-GFN
-3.506820.164143.83567.5059May 1, 2026

Evaluation results

MethodLinks
S-GFN2026.0587.6756.25
GFN2026.057.6719.86
ICL2026.057.330.72
Rainbow Teaming2026.054.670.46
Jailbreak R1CoT=enabled2026.052.670.26
PPO + Curiosity2026.050.330.03
SFT2026.0500
DPO2026.0500
PPO2026.0500