Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Text-based Jailbreak on JailbreakV_28K IND
Loading...
70.87
Attack Success Rate (ASR)
SelfReminder
-2.8348
16.3001
35.435
54.5699
Apr 7, 2026
Attack Success Rate (ASR)
Updated 9d ago
Evaluation Results
Method
Method
Links
Attack Success Rate (ASR)
SelfReminder
Base Model=LLaVA-1.5-13B
2026.04
70.87
CIDER
Base VLM=Qwen2.5-VL-7B...
2026.04
48.53
CIDER
Base Model=LLaVA-1.5-13B
2026.04
48.53
ECSO
Base Model=LLaVA-1.5-13B
2026.04
28.06
JailGuard
Base Model=LLaVA-1.5-13B
2026.04
26.33
ECSO
Base VLM=Qwen2.5-VL-7B...
2026.04
22.83
MirrorCheck
Base VLM=Qwen2.5-VL-7B...
2026.04
20.65
MirrorCheck
Base Model=LLaVA-1.5-13B
2026.04
20.65
JailGuard
Base VLM=Qwen2.5-VL-7B...
2026.04
16.18
VLMGuard
Base Model=LLaVA-1.5-13B
2026.04
9.26
SelfReminder
Base VLM=Qwen2.5-VL-7B...
2026.04
8.4
VLMGuard
Base VLM=Qwen2.5-VL-7B...
2026.04
5.72
ASTRA
Base Model=LLaVA-1.5-13B
2026.04
3.88
ASTRA
Base VLM=Qwen2.5-VL-7B...
2026.04
1.72
VLMShield
Base VLM=Qwen2.5-VL-7B...
2026.04
0
VLMShield
Base Model=LLaVA-1.5-13B
2026.04
0
Feedback
Search any
task
Search any
task