Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Defense against adversarial prompts on MMA (test)
Loading...
0.4
Attack Success Rate
DES
-2.5412
17.3119
37.165
57.0181
Jul 1, 2026
Attack Success Rate
Updated 23d ago
Evaluation Results
Method
Method
Links
Attack Success Rate
DES
Base Model=SDv1.5, Eva...
2026.07
0.4
SAGE
Base Model=SDv1.5, Eva...
2026.07
0.5
AdvUnlearn
Base Model=SDv1.5, Eva...
2026.07
2.1
SalUn
Base Model=SDv1.5, Eva...
2026.07
3.2
GLoCE
Base Model=SDv1.5, Eva...
2026.07
3.8
GuardT2I
Base Model=SDv1.5, Eva...
2026.07
7.54
ESD
Base Model=SDv1.5, Eva...
2026.07
8.5
Latent Guard
Base Model=SDv1.5, Eva...
2026.07
12.64
OpenAI
Base Model=SDv1.5, Eva...
2026.07
24.84
Microsoft
Base Model=SDv1.5, Eva...
2026.07
26.25
UCE
Base Model=SDv1.5, Eva...
2026.07
33.3
SAFREE
Base Model=SDv1.5, Eva...
2026.07
41.2
SLD-strong
Base Model=SDv1.5, Eva...
2026.07
59.2
SPM
Base Model=SDv1.5, Eva...
2026.07
65.05
SDv1.5
Base Model=SDv1.5, Eva...
2026.07
73.93
Feedback
Search any
task
Search any
task