Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Direct Malicious on VLSafe OOD
Loading...
90.67
ASR
SelfReminder
-1.942
22.1015
46.145
70.1885
Apr 7, 2026
ASR
Updated 9d ago
Evaluation Results
Method
Method
Links
ASR
SelfReminder
Base Model=LLaVA-1.5-13B
2026.04
90.67
JailGuard
Base Model=LLaVA-1.5-13B
2026.04
72.43
CIDER
Base VLM=Qwen2.5-VL-7B...
2026.04
50
CIDER
Base Model=LLaVA-1.5-13B
2026.04
50
JailGuard
Base VLM=Qwen2.5-VL-7B...
2026.04
31.35
MirrorCheck
Base VLM=Qwen2.5-VL-7B...
2026.04
26.33
MirrorCheck
Base Model=LLaVA-1.5-13B
2026.04
26.33
ECSO
Base Model=LLaVA-1.5-13B
2026.04
24
ECSO
Base VLM=Qwen2.5-VL-7B...
2026.04
19.63
VLMGuard
Base Model=LLaVA-1.5-13B
2026.04
15.27
VLMGuard
Base VLM=Qwen2.5-VL-7B...
2026.04
10.32
SelfReminder
Base VLM=Qwen2.5-VL-7B...
2026.04
8.55
ASTRA
Base Model=LLaVA-1.5-13B
2026.04
8.03
ASTRA
Base VLM=Qwen2.5-VL-7B...
2026.04
3.7
VLMShield
Base VLM=Qwen2.5-VL-7B...
2026.04
1.62
VLMShield
Base Model=LLaVA-1.5-13B
2026.04
1.62
Feedback
Search any
task
Search any
task