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

Jailbreak Attack Robustness on JBB-Behaviors

10ASR (PAIR)

RA

6.4830.245477.76Oct 1, 2025
Updated 4d ago

Evaluation Results

MethodLinks
2025.10
1072.345
2025.10
1671.747
2025.10
2578.370
2025.10
26.375.771.3
2025.10
27.377.766.3
2025.10
31.388.374
2025.10
3690.774.3
2025.10
36.794.371
2025.10
38.779.368.5
2025.10
3991.370.7
2025.10
44.392.781.3
2025.10
45.396.781.7
2025.10
46.381.755.3
2025.10
54.377.672
2025.10
5975.771
2025.10
67.582.385.7
2025.10
929593.5
2025.10
9879.393