Adversarially Robust Generalization Just Requires More Unlabeled Data
arXiv: Learning, 2019.
Neural network robustness has recently been highlighted by the existence of adversarial examples. Many previous works show that the learned networks do not perform well on perturbed test data, and significantly more labeled data is required to achieve adversarially robust generalization. In this paper, we theoretically and empirically s...More
PPT (Upload PPT)