Robustness of Deep ReLU Networks to Misclassification of High-Dimensional Data

Abstract

We present a theoretical study of the robustness of parameterized networks to random input perturbations. Specifically, we analyze local robustness at a given network input by quantifying the probability that a small additive random perturbation of the input leads to misclassification. For deep networks with rectified linear units, we derive lower bounds on local robustness in terms of the input dimensionality and the total number of network units.