List your company

Text-based Jailbreak on JailbreakV_28K IND

70.87Attack Success Rate (ASR)SelfReminder
-2.834816.300135.43554.5699Apr 7, 2026

Evaluation results

MethodLinks
SelfReminderBase Model=LLaVA-1.5-13B2026.0470.87
CIDERBase VLM=Qwen2.5-VL-7B-Instruct, Defense Category=External Defense2026.0448.53
CIDERBase Model=LLaVA-1.5-13B2026.0448.53
ECSOBase Model=LLaVA-1.5-13B2026.0428.06
JailGuardBase Model=LLaVA-1.5-13B2026.0426.33
ECSOBase VLM=Qwen2.5-VL-7B-Instruct, Defense Category=External Defense2026.0422.83
MirrorCheckBase VLM=Qwen2.5-VL-7B-Instruct, Defense Category=External Defense2026.0420.65
MirrorCheckBase Model=LLaVA-1.5-13B2026.0420.65
JailGuardBase VLM=Qwen2.5-VL-7B-Instruct, Defense Category=External Defense2026.0416.18
VLMGuardBase Model=LLaVA-1.5-13B2026.049.26
SelfReminderBase VLM=Qwen2.5-VL-7B-Instruct, Defense Category=External Defense2026.048.4
VLMGuardBase VLM=Qwen2.5-VL-7B-Instruct, Defense Category=Internal Defense2026.045.72
ASTRABase Model=LLaVA-1.5-13B2026.043.88
ASTRABase VLM=Qwen2.5-VL-7B-Instruct, Defense Category=Internal Defense2026.041.72
VLMShieldBase VLM=Qwen2.5-VL-7B-Instruct, Defense Category=External Defense2026.040
VLMShieldBase Model=LLaVA-1.5-13B2026.040