Adversarially Robust Generalization Requires More Data 1: A Robust-Error Lower Bound in the Gaussian ModelResearch Paper
Classifiers trained to high standard accuracy on image benchmarks can be made to fail by perturbations of the input that are small in the norm (Szegedy et al., 2014; Goodfellow et al., 2015). Adversarial training reaches high robust accuracy on the training set, but on CIFAR10 the robust accuracy on held-out data is much lower than on the…