List your company

Red-teaming on I2P Nudity prompts

0Failure Rate (FR)Ring-A-Bell
-2.294813.195128.68544.1749Nov 25, 2024

Evaluation results

MethodLinks
Ring-A-BellSafe T2I Model=Receler, Attack Access=black-box2024.110
PEZSafe T2I Model=AdvUnlearn, Attack Access=black-box2024.110.64
MMA-DiffusionSafe T2I Model=AdvUnlearn, Attack Access=white-box2024.110.86
PEZSafe T2I Model=RECE, Attack Access=black-box2024.110.86
PEZSafe T2I Model=ESD, Attack Access=black-box2024.111.07
PEZSafe T2I Model=Receler, Attack Access=black-box2024.111.5
Ring-A-BellSafe T2I Model=AdvUnlearn, Attack Access=black-box2024.112.11
SneakyPromptSafe T2I Model=AdvUnlearn, Attack Access=black-box2024.112.15
P4DSafe T2I Model=AdvUnlearn, Attack Access=white-box2024.113.22
UnlearnDiffAtkSafe T2I Model=AdvUnlearn, Attack Access=white-box2024.114.08
PEZSafe T2I Model=SAFREE, Attack Access=black-box2024.115.15
Flirt-ScoringSafe T2I Model=AdvUnlearn, Attack Access=black-box2024.116.22
MMA-DiffusionSafe T2I Model=RECE, Attack Access=white-box2024.116.44
UnlearnDiffAtkSafe T2I Model=SAFREE, Attack Access=white-box2024.116.44
SneakyPromptSafe T2I Model=SAFREE, Attack Access=black-box2024.117.3
SneakyPromptSafe T2I Model=RECE, Attack Access=black-box2024.117.3
SneakyPromptSafe T2I Model=Receler, Attack Access=black-box2024.118.58
PEZSafe T2I Model=SLD-MAX, Attack Access=black-box2024.119.87
P4DSafe T2I Model=SAFREE, Attack Access=white-box2024.1110.3
Ring-A-BellSafe T2I Model=ESD, Attack Access=black-box2024.1111.58
P4DSafe T2I Model=RECE, Attack Access=white-box2024.1111.59
MMA-DiffusionSafe T2I Model=ESD, Attack Access=white-box2024.1112.23
MMA-DiffusionSafe T2I Model=Receler, Attack Access=white-box2024.1112.23
UnlearnDiffAtkSafe T2I Model=Receler, Attack Access=white-box2024.1113.09
MMA-DiffusionSafe T2I Model=SAFREE, Attack Access=white-box2024.1113.73
SneakyPromptSafe T2I Model=ESD, Attack Access=black-box2024.1114.59
Flirt-ScoringSafe T2I Model=SAFREE, Attack Access=black-box2024.1114.59
Flirt-ScoringSafe T2I Model=Receler, Attack Access=black-box2024.1115.24
UnlearnDiffAtkSafe T2I Model=ESD, Attack Access=white-box2024.1116.95
UnlearnDiffAtkSafe T2I Model=RECE, Attack Access=white-box2024.1117.17
P4DSafe T2I Model=SLD-MAX, Attack Access=white-box2024.1117.38
ICERSafe T2I Model=AdvUnlearn, Attack Access=black-box2024.1117.6
P4DSafe T2I Model=Receler, Attack Access=white-box2024.1118.24
Ring-A-BellSafe T2I Model=RECE, Attack Access=black-box2024.1121.05
MMA-DiffusionSafe T2I Model=SLD-MAX, Attack Access=white-box2024.1123.82
Flirt-ScoringSafe T2I Model=RECE, Attack Access=black-box2024.1124.03
UnlearnDiffAtkSafe T2I Model=SLD-MAX, Attack Access=white-box2024.1124.25
Ring-A-BellSafe T2I Model=SAFREE, Attack Access=black-box2024.1125.26
Ring-A-BellSafe T2I Model=SLD-MAX, Attack Access=black-box2024.1126.32
ICERSafe T2I Model=RECE, Attack Access=black-box2024.1129.62
P4DSafe T2I Model=ESD, Attack Access=white-box2024.1133.05
Flirt-ScoringSafe T2I Model=ESD, Attack Access=black-box2024.1134.55
ICERSafe T2I Model=Receler, Attack Access=black-box2024.1136.27
ICERSafe T2I Model=SAFREE, Attack Access=black-box2024.1139.92
Flirt-ScoringSafe T2I Model=SLD-MAX, Attack Access=black-box2024.1142.06
SneakyPromptSafe T2I Model=SLD-MAX, Attack Access=black-box2024.1147
ICERSafe T2I Model=ESD, Attack Access=black-box2024.1148.71
ICERSafe T2I Model=SLD-MAX, Attack Access=black-box2024.1157.37