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

Jailbreak Attack on Prefilling Attack 40 tokens

0ASR (%)

Self-Reminder

-2.678815.403133.48551.5669Feb 2, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2026.02
01.03
2026.02
0.611.06
2026.02
0.611.08
2026.02
0.911.32
2026.02
1.211.08
2026.02
1.521.12
2026.02
1.521.37
2026.02
2.121.17
2026.02
2.731.68
2026.02
2.731.15
2026.02
3.031.66
2026.02
3.641.3
2026.02
3.641.3
2026.02
4.851.93
2026.02
5.151.75
2026.02
6.971.33
2026.02
6.971.62
2026.02
7.271.57
2026.02
7.581.58
2026.02
7.581.39
2026.02
7.581.77
2026.02
8.481.77
2026.02
8.481.7
2026.02
101.77
2026.02
11.521.83
2026.02
13.641.55
2026.02
14.852.36
2026.02
202.55
2026.02
20.912.42
2026.02
21.213.02
2026.02
21.822.89
2026.02
22.122.78
2026.02
25.152.72
2026.02
25.153.23
2026.02
26.973.33
2026.02
28.182.66
2026.02
302.99
2026.02
34.853.31
2026.02
39.73.53
2026.02
41.212.79
2026.02
46.363.7
2026.02
58.184.16
2026.02
65.764.34
2026.02
66.974.43
2026.02
66.974.43