Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Harmful prompt detection on adv-ViSU
Loading...
100
Precision
Detoxify (Orig)
39.68
55.34
71
86.66
Apr 7, 2026
Precision
Recall
F1 Score
Updated 10d ago
Evaluation Results
Method
Method
Links
Precision
Recall
F1 Score
Detoxify (Orig)
2026.04
100
7
13
DiffGuard
2026.04
97
40
65
HyPE
2026.04
97
67
80
NSFW-Classifier
2026.04
62
65
64
Latent Guard
2026.04
49
18
27
GuardT2I
2026.04
42
71
53
Feedback
Search any
task
Search any
task