Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Jailbreak Attack Robustness on FigStep jailbreak attack

17.44DSR

TGA-7B

-0.69764.01128.7213.4288Oct 16, 2024
Updated 4d ago

Evaluation Results

MethodLinks
2024.10
17.44
10.57
2024.10
2.91
2.47
2024.10
0.6
2024.10
0.58
2024.10
0