In this paper, we study adversarial training on datasets that obey the
long-tailed distribution, which is practical but rarely explored in previous
works. Compared with conventional adversarial training on balanced datasets,
this process falls into the dilemma of generating uneven adversarial examples
(AEs) and an unbalanced feature embedding space, causing the resulting model to
exhibit low robustness and accuracy on tail data. To combat that, we propose a
new adversarial training framework -- Re-balancing Adversarial Training (REAT).
This framework consists of two components: (1) a new training strategy inspired
by the term effective number to guide the model to generate more balanced and
informative AEs; (2) a carefully constructed penalty function to force a
satisfactory feature space. Evaluation results on different datasets and model
structures prove that REAT can effectively enhance the model's robustness and
preserve the model's clean accuracy. The code can be found in
this https URL

本文研究了在服从长尾分布的数据集上的对抗训练，相较于平衡数据集上的对抗训练，该过程会产生不均匀的对抗性样本和不平衡的特征嵌入空间，导致模型对尾部数据的鲁棒性和准确性低。为了解决这一问题，我们提出了一种新的对抗训练框架 —— 再平衡对抗训练（REAT），该框架包括两个组件：（1）通过有效数术语来指导模型生成更平衡和有信息的对抗性样本的新训练策略；（2）精心构建的惩罚函数来强制获得令人满意的特征空间。不同数据集和模型结构上的评估结果证明 REAT 可以有效提升模型的鲁棒性并保持模型的准确性。代码可以在此 URL 中找到。