Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

LLM Red-teaming on Rainbow Teaming defended Target Model

0UA

SFT

-4.425.35584.7May 1, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.05
00
2026.05
00
2026.05
0.330.03
0.330.03
2026.05
5.674.82
2026.05
9.670.94
2026.05
1464.13
181.76
2026.05
11083.24