A survey of robust adversarial training in pattern recognition: Fundamental, theory, and methodologies

作者：

Highlights：

• We present a timely and comprehensive survey on robust adversarial training.

• This survey offers the fundamentals of adversarial training, a unified theory that can be used to interpret various methods, and a comprehensive summarization of different methodologies.

• This survey also addresses three important research focus in adversarial training: interpretability, robust generalization, and robustness evaluation, which can stimulate future inspirations as well as research outlook.

摘要

•We present a timely and comprehensive survey on robust adversarial training.•This survey offers the fundamentals of adversarial training, a unified theory that can be used to interpret various methods, and a comprehensive summarization of different methodologies.•This survey also addresses three important research focus in adversarial training: interpretability, robust generalization, and robustness evaluation, which can stimulate future inspirations as well as research outlook.

论文关键词：Adversarial examples,Adversarial training,Robust learning

论文评审过程：Received 3 March 2022, Revised 14 June 2022, Accepted 3 July 2022, Available online 5 July 2022, Version of Record 9 July 2022.

论文官网地址：https://doi.org/10.1016/j.patcog.2022.108889