TL;DR本论文提出了一种基于半隐式杂交梯度法的对抗学习算法，能够显著提高收敛速度和稳健性，并证明其在解决非凸非凹极小极大问题上的收敛率优于动态对抗训练算法和You Only Propagate Once算法。
Abstract
adversarial examples, crafted by adding imperceptible perturbations to natural inputs, can easily fool deep neural networks (DNNs). One of the most successful methods for training adversarially robust DNNs is sol