List your company
ResearchFormerly WizWand

Adversarial Robust Image Classification on CIFAR-10 (test) (PGD20 & CW40)

61.88Robust Accuracy (PGD-20)RobustResNet-A4
52.062454.611257.1659.7088Dec 21, 2022
Updated 8mo ago

Evaluation results

MethodLinks
RobustResNet-A4#P (M)=147, #F (G)=39.4, Adversarial Training Protocol=MART2022.1261.8857.55
RobustResNet-A3#P (M)=75.9, #F (G)=19.9, Adversarial Training Protocol=MART2022.1260.9556.52
RobustResNet-A2#P (M)=39.0, #F (G)=10.8, Adversarial Training Protocol=MART2022.1260.3355.51
RobustResNet-A1#P (M)=19.2, #F (G)=5.11, Adversarial Training Protocol=MART2022.1259.3454.42
RobustResNet-A4#P (M)=147, #F (G)=39.4, Adversarial Training Protocol=SAT2022.1259.0157.85
RobustResNet-A3#P (M)=75.9, #F (G)=19.9, Adversarial Training Protocol=SAT2022.1258.8157.6
WRN-46-14#P (M)=128, #F (G)=18.6, Adversarial Training Protocol=MART2022.1258.4354.32
RobustResNet-A2#P (M)=39.0, #F (G)=10.8, Adversarial Training Protocol=SAT2022.1258.3956.99
WRN-70-16#P (M)=267, #F (G)=38.8, Adversarial Training Protocol=MART2022.1258.1554.37
WRN-28-10#P (M)=36.5, #F (G)=5.20, Adversarial Training Protocol=MART2022.1257.6952.88
RobustResNet-A1#P (M)=19.2, #F (G)=5.11, Adversarial Training Protocol=SAT2022.1257.6256.06
WRN-34-12#P (M)=66.5, #F (G)=9.60, Adversarial Training Protocol=MART2022.1257.453.11
WRN-70-16#P (M)=267, #F (G)=38.8, Adversarial Training Protocol=SAT2022.1254.1250.52
WRN-46-14#P (M)=128, #F (G)=18.6, Adversarial Training Protocol=SAT2022.1253.6752.95
WRN-34-12#P (M)=66.5, #F (G)=9.60, Adversarial Training Protocol=SAT2022.1252.8551.36
WRN-28-10#P (M)=36.5, #F (G)=5.20, Adversarial Training Protocol=SAT2022.1252.4450.97