Adversarial training is one of the most effective approaches defending against adversarial examples for deep learning models. Unlike other defenses that are limited to specific tasks, adversarial training is more general and can be extended easily. However, adversarial training is not perfect, many problems of which remain to be solved. During the last few years, adversarial training is being studied and discussed from various aspects, and many improvements and developments are proposed. In this survey, we systematically review the recent progress on adversarial training with novel taxonomy for the first time. Then we discuss the generalization problems in adversarial training from three perspectives. Finally, we highlight the challenges which are not fully solved and present potential future directions.

翻译：对抗性培训是防止激烈学习模式的对抗性实例的最有效方法之一。与其他限于具体任务的防御性培训不同,对抗性培训比较笼统,可以轻易扩展。然而,对抗性培训并不完美,许多问题仍有待解决。在过去几年里,从各方面研究和讨论对抗性培训,并提出了许多改进和发展建议。在本次调查中,我们首次系统地审查了以新分类法进行的对抗性培训的最新进展。然后,我们从三个角度讨论了对抗性培训的普遍化问题。最后,我们强调了尚未完全解决的挑战,并提出了潜在的未来方向。