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

Jailbreak Defense and Utility Evaluation on Implicit Risk Finance Dataset

0.4Jailbreak Success Rate (JSR)

MENTOR

-2.88819.30641.563.694Nov 10, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.11
0.44.918
2025.11
0.64.368
2025.11
0.64.856
2025.11
14.908
2025.11
1.64.386
2025.11
1.64.544
2025.11
2.44.776
2025.11
2.84.516
2025.11
34.642
2025.11
5.84.7
2025.11
6.84.472
2025.11
84.396
2025.11
9.24.534
2025.11
9.44.72
2025.11
124.678
2025.11
26.84.77
2025.11
28.84.316
2025.11
304.854
2025.11
32.24.796
2025.11
39.24.892
2025.11
47.84.456
2025.11
48.44.78
2025.11
52.24.924
2025.11
57.24.878
2025.11
58.64.922
2025.11
63.24.166
2025.11
64.24.066
2025.11
72.64.442
2025.11
754.564
2025.11
82.64.65