Styx: a data-oriented mutation framework to improve the robustness of DNN

Deep neural networks (DNN) have been shown to be notoriously brittle to small perturbations in their input data. This problem is analogous to the over-fitting problem in test-based program synthesis and automatic program repair, which is a consequence of ...

Deep neural networks (DNNs) have achieved unprecedented accomplishments in various machine learning tasks. However, recent studies demonstrate that DNNs are extremely vulnerable to adversarial examples. They are manually synthesized input samples which ...

We study the model robustness against adversarial examples, referred to as small perturbed input data that may however fool many state-of-the-art deep learning models. Unlike previous research, we establish a novel theory addressing the robustness ...