Out-distribution training confers robustness to deep neural networks

The easiness at which adversarial instances can be generated in deep neural networks raises some fundamental questions on their functioning and concerns on their use in critical systems. In this paper, we draw a connection between overgeneralization and adversaries: a possible cause of adversaries lies in models designed to make decisions all over the input space, leading to inappropriate highconfidence decisions in parts of the input space not represented in the training set. We empirically show an augmented neural network, which is not trained on any types of adversaries, can increase the robustness by detecting black-box one-step adversaries, i.e. assimilated to out-distribution samples, and making generation of white-box one-step adversaries harder.