Differentiable Search of Accurate and Robust Architectures. (arXiv:2212.14049v1 [cs.LG])

Deep neural networks (DNNs) are found to be vulnerable to adversarial
attacks, and various methods have been proposed for the defense. Among these
methods, adversarial training has been drawing increasing attention because of
its simplicity and effectiveness. However, the performance of the adversarial
training is greatly limited by the architectures of target DNNs, which often
makes the resulting DNNs with poor accuracy and unsatisfactory robustness. To
address this problem, we propose DSARA to automatically search for the neural
architectures that …

adversarial adversarial attacks attacks attention defense drawing networks neural networks performance search training vulnerable