Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Malicious Prompt Detection on GPT4V-Caption (IOD)
Loading...
0
FPR
VLMShield
-0.3176
1.8262
3.97
6.1138
Apr 7, 2026
FPR
Updated 9d ago
Evaluation Results
Method
Method
Links
FPR
VLMShield
Target Model=LLaVA-1.5...
2026.04
0
VLMShield
Target Model=Qwen2.5-V...
2026.04
0
CIDER
Target Model=LLaVA-1.5...
2026.04
2.2
CIDER
Target Model=Qwen2.5-V...
2026.04
2.2
ASTRA
Target Model=Qwen2.5-V...
2026.04
2.26
JailGuard
Target Model=Qwen2.5-V...
2026.04
2.64
VLMGuard
Target Model=Qwen2.5-V...
2026.04
2.67
ECSO
Target Model=Qwen2.5-V...
2026.04
3.7
ASTRA
Target Model=LLaVA-1.5...
2026.04
3.85
VLMGuard
Target Model=LLaVA-1.5...
2026.04
4.76
JailGuard
Target Model=LLaVA-1.5...
2026.04
4.91
ECSO
Target Model=LLaVA-1.5...
2026.04
6.02
MirrorCheck
Target Model=LLaVA-1.5...
2026.04
7.94
MirrorCheck
Target Model=Qwen2.5-V...
2026.04
7.94
Feedback
Search any
task
Search any
task
