Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Malicious Prompt Detection on JailbreakV_28K Text-based (test)
Loading...
0
FNR
VLMShield
-2.8348
16.3001
35.435
54.5699
Apr 7, 2026
FNR
Updated 9d ago
Evaluation Results
Method
Method
Links
FNR
VLMShield
Target VLM Architectur...
2026.04
0
VLMShield
Target VLM Architectur...
2026.04
0
ASTRA
Target VLM Architectur...
2026.04
1.72
ASTRA
Target VLM Architectur...
2026.04
3.88
VLMGuard
Target VLM Architectur...
2026.04
5.72
SelfReminder
Target VLM Architectur...
2026.04
8.4
VLMGuard
Target VLM Architectur...
2026.04
9.26
JailGuard
Target VLM Architectur...
2026.04
16.18
MirrorCheck
Target VLM Architectur...
2026.04
20.65
MirrorCheck
Target VLM Architectur...
2026.04
20.65
ECSO
Target VLM Architectur...
2026.04
22.83
JailGuard
Target VLM Architectur...
2026.04
26.33
ECSO
Target VLM Architectur...
2026.04
28.06
CIDER
Target VLM Architectur...
2026.04
48.53
CIDER
Target VLM Architectur...
2026.04
48.53
SelfReminder
Target VLM Architectur...
2026.04
70.87
Feedback
Search any
task
Search any
task