Abstract
Deep neural networks have been found to be vulnerable to adversarial attacks. To address this challenge, this paper adopts the evolutionary multi-objective approach to the learning process, and manages to achieve a balance between learning accuracy and robustness against adversarial attacks. In addition, we propose to minimize the model complexity together with the adversarial training loss to defend against fast gradient signed method attacks. Our experimental results using two deep neural networks models, LeNet-5 and VGG-11, on MNIST and CIFAR-10 datasets, respectively, confirm that the proposed methods are effective in improving the robustness of deep learning models against adversarial attacks.