madrylab/robust-imagenet-models

Overview

This repository contains the robust ImageNet models used in our paper "Do adversarially robust imagenet models transfer better?".

See our papers's GitHub repository for more details!

Summary of our pretrained models

Standard Accuracy of L2-Robust ImageNet Models

Model	ε=0	ε=0.01	ε=0.03	ε=0.05	ε=0.1	ε=0.25	ε=0.5	ε=1.0	ε=3.0	ε=5.0
ResNet-18	69.79	69.90	69.24	69.15	68.77	67.43	65.49	62.32	53.12	45.59
ResNet-50	75.80	75.68	75.76	75.59	74.78	74.14	73.16	70.43	62.83	56.13
Wide-ResNet-50-2	76.97	77.25	77.26	77.17	76.74	76.21	75.11	73.41	66.90	60.94
Wide-ResNet-50-4	77.91	78.02	77.87	77.77	77.64	77.10	76.52	75.51	69.67	65.20

Model	ε=0	ε=3
DenseNet	77.37	66.98
MNASNET	60.97	41.83
MobileNet-v2	65.26	50.40
ResNeXt50_32x4d	77.38	66.25
ShuffleNet	64.25	43.32
VGG16_bn	73.66	57.19

Standard Accuracy of Linf-Robust ImageNet Models

Model	ε=0.5/255	ε=1/255	ε=2/255	ε=4/255	ε=8/255
ResNet-18	66.13	63.46	59.63	52.49	42.11
ResNet-50	73.73	72.05	69.10	63.86	54.53
Wide-ResNet-50-2	75.82	74.65	72.35	68.41	60.82