Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Text-based Jailbreak on AdvBench-M OOD
Loading...
61.3
ASR (OOD)
CIDER
-2.0256
14.4147
30.855
47.2953
Apr 7, 2026
ASR (OOD)
Updated 9d ago
Evaluation Results
Method
Method
Links
ASR (OOD)
CIDER
Base VLM=Qwen2.5-VL-7B...
2026.04
61.3
CIDER
Base Model=LLaVA-1.5-13B
2026.04
61.3
SelfReminder
Base Model=LLaVA-1.5-13B
2026.04
42.65
JailGuard
Base Model=LLaVA-1.5-13B
2026.04
40.02
MirrorCheck
Base VLM=Qwen2.5-VL-7B...
2026.04
30.15
MirrorCheck
Base Model=LLaVA-1.5-13B
2026.04
30.15
JailGuard
Base VLM=Qwen2.5-VL-7B...
2026.04
27.49
ECSO
Base Model=LLaVA-1.5-13B
2026.04
22.09
ECSO
Base VLM=Qwen2.5-VL-7B...
2026.04
17.06
ASTRA
Base Model=LLaVA-1.5-13B
2026.04
13.48
VLMGuard
Base Model=LLaVA-1.5-13B
2026.04
9.84
VLMGuard
Base VLM=Qwen2.5-VL-7B...
2026.04
8.66
SelfReminder
Base VLM=Qwen2.5-VL-7B...
2026.04
6.72
ASTRA
Base VLM=Qwen2.5-VL-7B...
2026.04
6.33
VLMShield
Base VLM=Qwen2.5-VL-7B...
2026.04
0.41
VLMShield
Base Model=LLaVA-1.5-13B
2026.04
0.41
Feedback
Search any
task
Search any
task