List your company

Text-based Jailbreak on AdvBench-M OOD

61.3ASR (OOD)CIDER
-2.025614.414730.85547.2953Apr 7, 2026

Evaluation results

MethodLinks
CIDERBase VLM=Qwen2.5-VL-7B-Instruct, Defense Category=External Defense2026.0461.3
CIDERBase Model=LLaVA-1.5-13B2026.0461.3
SelfReminderBase Model=LLaVA-1.5-13B2026.0442.65
JailGuardBase Model=LLaVA-1.5-13B2026.0440.02
MirrorCheckBase VLM=Qwen2.5-VL-7B-Instruct, Defense Category=External Defense2026.0430.15
MirrorCheckBase Model=LLaVA-1.5-13B2026.0430.15
JailGuardBase VLM=Qwen2.5-VL-7B-Instruct, Defense Category=External Defense2026.0427.49
ECSOBase Model=LLaVA-1.5-13B2026.0422.09
ECSOBase VLM=Qwen2.5-VL-7B-Instruct, Defense Category=External Defense2026.0417.06
ASTRABase Model=LLaVA-1.5-13B2026.0413.48
VLMGuardBase Model=LLaVA-1.5-13B2026.049.84
VLMGuardBase VLM=Qwen2.5-VL-7B-Instruct, Defense Category=Internal Defense2026.048.66
SelfReminderBase VLM=Qwen2.5-VL-7B-Instruct, Defense Category=External Defense2026.046.72
ASTRABase VLM=Qwen2.5-VL-7B-Instruct, Defense Category=Internal Defense2026.046.33
VLMShieldBase VLM=Qwen2.5-VL-7B-Instruct, Defense Category=External Defense2026.040.41
VLMShieldBase Model=LLaVA-1.5-13B2026.040.41