List your company

Red-teaming on Violence prompts

0Failure Rate (FR)UnlearnDiffAtk
-2.469214.197930.86547.5321Nov 25, 2024

Evaluation results

MethodLinks
UnlearnDiffAtkSafe T2I Model=RECE, Attack Access=white-box2024.110
PEZSafe T2I Model=Receler, Attack Access=black-box2024.110.74
PEZSafe T2I Model=AdvUnlearn, Attack Access=black-box2024.111.85
Ring-A-BellSafe T2I Model=AdvUnlearn, Attack Access=black-box2024.113.2
PEZSafe T2I Model=SLD-MAX, Attack Access=black-box2024.113.7
SneakyPromptSafe T2I Model=AdvUnlearn, Attack Access=black-box2024.114.05
PEZSafe T2I Model=ESD, Attack Access=black-box2024.114.63
Ring-A-BellSafe T2I Model=ESD, Attack Access=black-box2024.114.8
P4DSafe T2I Model=SLD-MAX, Attack Access=white-box2024.115.56
Ring-A-BellSafe T2I Model=SLD-MAX, Attack Access=black-box2024.115.6
Ring-A-BellSafe T2I Model=Receler, Attack Access=black-box2024.115.6
Ring-A-BellSafe T2I Model=RECE, Attack Access=black-box2024.115.6
MMA-DiffusionSafe T2I Model=AdvUnlearn, Attack Access=white-box2024.116.02
Flirt-ScoringSafe T2I Model=RECE, Attack Access=black-box2024.116.02
MMA-DiffusionSafe T2I Model=Receler, Attack Access=white-box2024.116.38
MMA-DiffusionSafe T2I Model=SLD-MAX, Attack Access=white-box2024.116.94
SneakyPromptSafe T2I Model=Receler, Attack Access=black-box2024.117.01
P4DSafe T2I Model=SAFREE, Attack Access=white-box2024.117.41
UnlearnDiffAtkSafe T2I Model=SLD-MAX, Attack Access=white-box2024.117.41
SneakyPromptSafe T2I Model=SAFREE, Attack Access=black-box2024.119.72
MMA-DiffusionSafe T2I Model=ESD, Attack Access=white-box2024.1111.11
Flirt-ScoringSafe T2I Model=AdvUnlearn, Attack Access=black-box2024.1111.57
MMA-DiffusionSafe T2I Model=SAFREE, Attack Access=white-box2024.1113.43
P4DSafe T2I Model=AdvUnlearn, Attack Access=white-box2024.1113.89
P4DSafe T2I Model=RECE, Attack Access=white-box2024.1113.89
UnlearnDiffAtkSafe T2I Model=AdvUnlearn, Attack Access=white-box2024.1114.35
PEZSafe T2I Model=SAFREE, Attack Access=black-box2024.1114.81
UnlearnDiffAtkSafe T2I Model=SAFREE, Attack Access=white-box2024.1115.74
SneakyPromptSafe T2I Model=RECE, Attack Access=black-box2024.1117.13
SneakyPromptSafe T2I Model=ESD, Attack Access=black-box2024.1117.14
SneakyPromptSafe T2I Model=SLD-MAX, Attack Access=black-box2024.1119.16
MMA-DiffusionSafe T2I Model=RECE, Attack Access=white-box2024.1122.69
ICERSafe T2I Model=AdvUnlearn, Attack Access=black-box2024.1123.3
Ring-A-BellSafe T2I Model=SAFREE, Attack Access=black-box2024.1124
Flirt-ScoringSafe T2I Model=Receler, Attack Access=black-box2024.1124.07
Flirt-ScoringSafe T2I Model=SAFREE, Attack Access=black-box2024.1127.78
Flirt-ScoringSafe T2I Model=SLD-MAX, Attack Access=black-box2024.1130.09
P4DSafe T2I Model=Receler, Attack Access=white-box2024.1130.56
UnlearnDiffAtkSafe T2I Model=Receler, Attack Access=white-box2024.1130.56
PEZSafe T2I Model=RECE, Attack Access=black-box2024.1136.57
P4DSafe T2I Model=ESD, Attack Access=white-box2024.1137.96
UnlearnDiffAtkSafe T2I Model=ESD, Attack Access=white-box2024.1138.89
Flirt-ScoringSafe T2I Model=ESD, Attack Access=black-box2024.1138.89
ICERSafe T2I Model=Receler, Attack Access=black-box2024.1142.75
ICERSafe T2I Model=SLD-MAX, Attack Access=black-box2024.1144.91
ICERSafe T2I Model=SAFREE, Attack Access=black-box2024.1147.45
ICERSafe T2I Model=RECE, Attack Access=black-box2024.1158.11
ICERSafe T2I Model=ESD, Attack Access=black-box2024.1161.73