Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Defense against adversarial prompts on P4D (test)
Loading...
1.1
Attack Success Rate
AdvUnlearn
-2.6532
22.6809
48.015
73.3491
Jul 1, 2026
Attack Success Rate
Updated 23d ago
Evaluation Results
Method
Method
Links
Attack Success Rate
AdvUnlearn
Base Model=SDv1.5, Eva...
2026.07
1.1
DES
Base Model=SDv1.5, Eva...
2026.07
1.1
SAGE
Base Model=SDv1.5, Eva...
2026.07
1.1
SalUn
Base Model=SDv1.5, Eva...
2026.07
5.15
GLoCE
Base Model=SDv1.5, Eva...
2026.07
5.51
GuardT2I
Base Model=SDv1.5, Eva...
2026.07
8.31
ESD
Base Model=SDv1.5, Eva...
2026.07
26.1
UCE
Base Model=SDv1.5, Eva...
2026.07
33.09
Latent Guard
Base Model=SDv1.5, Eva...
2026.07
47.11
SAFREE
Base Model=SDv1.5, Eva...
2026.07
48.9
OpenAI
Base Model=SDv1.5, Eva...
2026.07
58.98
SLD-strong
Base Model=SDv1.5, Eva...
2026.07
62.5
SPM
Base Model=SDv1.5, Eva...
2026.07
71.32
Microsoft
Base Model=SDv1.5, Eva...
2026.07
72.24
SDv1.5
Base Model=SDv1.5, Eva...
2026.07
94.93
Feedback
Search any
task
Search any
task