List your company

Jailbreak Attack on Malicious goals dataset (test)

0ASRFigStep
-3.9422.65549.2575.845Oct 20, 2025

Evaluation results

MethodLinks
FigStepInput Modality=Multimodal, Target Model=Claude-3-7-Sonnet2025.1001.03
HadesInput Modality=Multimodal, Target Model=Claude-3-7-Sonnet2025.1001.016
Query-AttackInput Modality=Multimodal, Target Model=Gemini-2.5-Flash2025.1001.008
Query-AttackInput Modality=Multimodal, Target Model=Claude-3-7-Sonnet2025.1001.013
MML-MInput Modality=Multimodal, Target Model=Claude-3-7-Sonnet2025.1001.014
MM-SafetyBenchInput Modality=Multimodal, Target Model=Claude-3-7-Sonnet2025.100.51.03
JOODInput Modality=Text-only, Target Model=Claude-3-7-Sonnet2025.100.751.054
Query-AttackInput Modality=Multimodal, Target Model=GPT-4.12025.100.751.05
Query-AttackInput Modality=Multimodal, Target Model=GPT-4o2025.1021.134
FigStepInput Modality=Multimodal, Target Model=GPT-4.12025.102.251.087
FigStepInput Modality=Multimodal, Target Model=GPT-4o2025.1031.108
HadesInput Modality=Multimodal, Target Model=GPT-4.12025.103.751.209
MML-MInput Modality=Multimodal, Target Model=GPT-4.12025.103.751.181
FigStepInput Modality=Multimodal, Target Model=Gemini-2.5-Flash2025.105.251.184
HadesInput Modality=Multimodal, Target Model=LLaMA3.2-Vision2025.1061.255
ArtPromptInput Modality=Text-only, Target Model=Claude-3-7-Sonnet2025.106.251.382
MML-MInput Modality=Multimodal, Target Model=LLaMA3.2-Vision2025.106.51.297
MM-SafetyBenchInput Modality=Multimodal, Target Model=GPT-4.12025.107.51.197
DRAInput Modality=Text-only, Target Model=Claude-3-7-Sonnet2025.108.252.617
MML-MInput Modality=Multimodal, Target Model=Gemini-2.5-Flash2025.108.51.319
HadesInput Modality=Multimodal, Target Model=Gemini-2.5-Flash2025.1091.317
MM-SafetyBenchInput Modality=Multimodal, Target Model=LLaMA3.2-Vision2025.10101.36
MM-SafetyBenchInput Modality=Multimodal, Target Model=Gemini-2.5-Flash2025.10101.343
ArtPromptInput Modality=Text-only, Target Model=LLaVA-v1.62025.1012.752.565
FlipAttackInput Modality=Text-only, Target Model=LLaVA-v1.52025.1013.252.486
ArtPromptInput Modality=Text-only, Target Model=Qwen2.5-VL2025.1013.751.55
HadesInput Modality=Multimodal, Target Model=GPT-4o2025.1014.251.535
MML-MInput Modality=Multimodal, Target Model=GPT-4o2025.1014.751.54
MML-MInput Modality=Multimodal, Target Model=Qwen2.5-VL2025.1015.51.714
MML-MInput Modality=Multimodal, Target Model=Average2025.1016.661.654
HadesInput Modality=Multimodal, Target Model=Qwen2.5-VL2025.1016.751.788
JOODInput Modality=Text-only, Target Model=GPT-4.12025.1017.51.605
FlipAttackInput Modality=Text-only, Target Model=Qwen2.5-VL2025.1017.52.743
Query-AttackInput Modality=Multimodal, Target Model=LLaMA3.2-Vision2025.1017.51.137
JOODInput Modality=Text-only, Target Model=Qwen2.5-VL2025.1018.251.861
Query-AttackInput Modality=Multimodal, Target Model=Average2025.1018.631.562
MM-SafetyBenchInput Modality=Multimodal, Target Model=GPT-4o2025.1018.751.593
HadesInput Modality=Multimodal, Target Model=Average2025.1019.631.79
JOODInput Modality=Text-only, Target Model=Gemini-2.5-Flash2025.10231.915
ArtPromptInput Modality=Text-only, Target Model=GPT-4.12025.1023.51.736
MM-SafetyBenchInput Modality=Multimodal, Target Model=Qwen2.5-VL2025.1023.52.054
Query-AttackInput Modality=Multimodal, Target Model=Qwen2.5-VL2025.1023.51.107
DRAInput Modality=Text-only, Target Model=GPT-4o2025.10242.752
FigStepInput Modality=Multimodal, Target Model=Qwen2.5-VL2025.10242.035
FlipAttackInput Modality=Text-only, Target Model=LLaVA-v1.62025.1024.53.106
JOODInput Modality=Text-only, Target Model=Average2025.1024.881.961
MM-SafetyBenchInput Modality=Multimodal, Target Model=Average2025.1026.061.967
ArtPromptInput Modality=Text-only, Target Model=Average2025.1026.382.092
Query-AttackInput Modality=Multimodal, Target Model=LLaVA-v1.62025.1027.52.047
JOODInput Modality=Text-only, Target Model=LLaMA3.2-Vision2025.1028.251.9
ArtPromptInput Modality=Text-only, Target Model=LLaMA3.2-Vision2025.10291.975
JOODInput Modality=Text-only, Target Model=LLaVA-v1.52025.1029.52.189
DarkCiteInput Modality=Text-only, Target Model=Claude-3-7-Sonnet2025.1029.751.59
JOODInput Modality=Text-only, Target Model=GPT-4o2025.1031.52.259
FigStepInput Modality=Multimodal, Target Model=Average2025.1032.252.243
PolyJailbreakInput Modality=Multimodal, Target Model=Claude-3-7-Sonnet2025.1034.53.179
ArtPromptInput Modality=Text-only, Target Model=Gemini-2.5-Flash2025.1035.52.132
ArtPromptInput Modality=Text-only, Target Model=GPT-4o2025.1035.752.207
MML-MInput Modality=Multimodal, Target Model=LLaVA-v1.62025.1037.542.354
FlipAttackInput Modality=Text-only, Target Model=Claude-3-7-Sonnet2025.10463.165
MML-MInput Modality=Multimodal, Target Model=LLaVA-v1.52025.1046.752.81
DRAInput Modality=Text-only, Target Model=GPT-4.12025.10503.684
JOODInput Modality=Text-only, Target Model=LLaVA-v1.62025.1050.252.905
HadesInput Modality=Multimodal, Target Model=LLaVA-v1.62025.1050.752.904
FlipAttackInput Modality=Text-only, Target Model=LLaMA3.2-Vision2025.1053.53.25
FlipAttackInput Modality=Text-only, Target Model=Average2025.1054.063.633
DRAInput Modality=Text-only, Target Model=Average2025.1054.193.874
ArtPromptInput Modality=Text-only, Target Model=LLaVA-v1.52025.1054.53.187
HadesInput Modality=Multimodal, Target Model=LLaVA-v1.52025.1056.53.299
DarkCiteInput Modality=Text-only, Target Model=LLaMA3.2-Vision2025.10582.385
DarkCiteInput Modality=Text-only, Target Model=Gemini-2.5-Flash2025.1058.752.664
MM-SafetyBenchInput Modality=Multimodal, Target Model=LLaVA-v1.62025.10623.333
FigStepInput Modality=Multimodal, Target Model=LLaMA3.2-Vision2025.1062.753.28
DRAInput Modality=Text-only, Target Model=LLaVA-v1.52025.10644.301
DRAInput Modality=Text-only, Target Model=Qwen2.5-VL2025.1064.254.249
DarkCiteInput Modality=Text-only, Target Model=Average2025.1065.192.526
DarkCiteInput Modality=Text-only, Target Model=GPT-4o2025.10682.394
DRAInput Modality=Text-only, Target Model=LLaVA-v1.62025.10694.389
DRAInput Modality=Text-only, Target Model=LLaMA3.2-Vision2025.1071.754.463
DarkCiteInput Modality=Text-only, Target Model=LLaVA-v1.52025.1071.752.709
DarkCiteInput Modality=Text-only, Target Model=GPT-4.12025.1075.52.598
PolyJailbreakInput Modality=Multimodal, Target Model=LLaMA3.2-Vision2025.1075.943.517
FigStepInput Modality=Multimodal, Target Model=LLaVA-v1.52025.1076.254.062
MM-SafetyBenchInput Modality=Multimodal, Target Model=LLaVA-v1.52025.1076.253.829
DarkCiteInput Modality=Text-only, Target Model=Qwen2.5-VL2025.1077.252.937
Query-AttackInput Modality=Multimodal, Target Model=LLaVA-v1.52025.1077.753.998
PolyJailbreakInput Modality=Multimodal, Target Model=Qwen2.5-VL2025.10803.762
DRAInput Modality=Text-only, Target Model=Gemini-2.5-Flash2025.1082.254.536
DarkCiteInput Modality=Text-only, Target Model=LLaVA-v1.62025.1082.52.934
PolyJailbreakInput Modality=Multimodal, Target Model=Average2025.1083.343.976
FigStepInput Modality=Multimodal, Target Model=LLaVA-v1.62025.1084.54.154
PolyJailbreakInput Modality=Multimodal, Target Model=GPT-4.12025.10864.118
FlipAttackInput Modality=Text-only, Target Model=GPT-4.12025.1090.54.691
FlipAttackInput Modality=Text-only, Target Model=GPT-4o2025.1090.754.769
FlipAttackInput Modality=Text-only, Target Model=Gemini-2.5-Flash2025.1096.54.857
PolyJailbreakInput Modality=Multimodal, Target Model=LLaVA-v1.62025.10974.443
PolyJailbreakInput Modality=Multimodal, Target Model=Gemini-2.5-Flash2025.1097.254.343
PolyJailbreakInput Modality=Multimodal, Target Model=GPT-4o2025.1097.54.28
PolyJailbreakInput Modality=Multimodal, Target Model=LLaVA-v1.52025.1098.54.164