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

Jailbreaking Attack on MM-SafetyBench

95Attack Success Rate (ASR)

TAO-Attack

-3.404822.142647.6973.2374Jan 8, 2026Feb 6, 2026Mar 7, 2026Apr 6, 2026May 5, 2026Jun 3, 2026Jul 3, 2026
Updated 19d ago

Evaluation Results

MethodLinks
2026.03
95132
2026.05
93.75-
2026.05
93.1-
2026.01
91.5-
2026.05
91.25-
2026.07
90.68-
2026.05
90.42-
2026.03
90248
2026.05
88.45-
2026.07
87.41-
2026.07
86.25-
2026.05
86.24-
2026.07
83.92-
2026.05
82.86-
2026.07
82.75-
2026.05
82.02-
2026.07
81-
2026.05
80.65-
2026.05
80.54-
2026.05
79.4-
2026.07
79.02-
2026.07
78.79-
2026.01
77.31-
2026.07
76.57-
2026.07
76.46-
2026.07
75.06-
2026.07
74.83-
2026.07
74.48-
2026.07
72.26-
2026.01
72.14-
2026.07
69.7-
2026.01
68.57-
2026.07
63.4-
2026.01
62.68-
2026.01
62.3-
2026.07
57.81-
2026.07
56.41-
2026.07
56.18-
2026.07
54.66-
2026.07
54.19-
2026.07
53.38-
2026.07
53.26-
2026.07
53.26-
2026.07
51.75-
2026.07
45.22-
2026.07
44.17-
2026.07
39.86-
2026.07
38.23-
2026.07
33.45-
2026.07
31-
2026.07
30.42-
2026.05
29.4-
2026.05
28.93-
2026.05
28.27-
2026.07
27.51-
2026.05
26.9-
2026.05
25.48-
2026.05
21.3-
2026.07
20.98-
2026.01
19.81-
2026.07
19.7-
2026.05
19.29-
2026.07
18.53-
2026.05
16.49-
2026.05
15.24-
2026.07
14.8-
2026.07
12.59-
2026.01
12.34-
2026.05
11.73-
2026.05
11.31-
2026.07
10.37-
10-
2026.04
7.31-
2026.07
4.43-
2026.04
2.69-
2026.04
2.69-
1.54-
0.77-
0.77-
2026.04
0.77-
0.77-
2026.04
0.38-