Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Text-to-Image Jailbreak Attack on NSFW-200
Loading...
100
Attack Success Rate (Paper)
SneakyPrompt
95
97.5
100
102.5
Jun 23, 2026
Attack Success Rate (Paper)
Attack Success Rate (Gen)
Difference in Attack Success Rate (Paper - Gen)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Attack Success Rate (Paper)
Attack Success Rate (Gen)
Difference in Attack Success Rate (Paper - Gen)
SneakyPrompt
Evaluation Metric=Bypa...
2026.06
100
100
0
JailFuzzer
Evaluation Metric=Bypa...
2026.06
100
100
0
PGJ
Evaluation Metric=ASR-...
2026.06
100
92.8
7.2
Feedback
Search any
task
Search any
task