Adversarial training is an important topic in robust deep learning, but the community lacks attention to its practical usage. In this paper, we aim to resolve a real-world challenge, i.e., training a model on an imbalanced and noisy dataset to achieve high clean accuracy and adversarial robustness, with our proposed Omnipotent Adversarial Training (OAT) strategy. OAT consists of two innovative methodologies to address the imperfection in the training set. We first introduce an oracle into the adversarial training process to help the model learn a correct data-label conditional distribution. This carefully-designed oracle can provide correct label annotations for adversarial training. We further propose logits adjustment adversarial training to overcome the data imbalance issue, which can help the model learn a Bayes-optimal distribution. Our comprehensive evaluation results show that OAT outperforms other baselines by more than 20% clean accuracy improvement and 10% robust accuracy improvement under complex combinations of data imbalance and label noise scenarios. The code can be found in https://github.com/GuanlinLee/OAT.

翻译：对抗训练是鲁棒深度学习中的重要课题，但学术界对其实际应用场景的关注仍显不足。本文旨在解决现实世界的挑战，即在不平衡且含噪的数据集上训练模型，以同时实现高干净精度和对抗鲁棒性，我们提出的全能对抗训练（OAT）策略应运而生。OAT包含两种创新方法以应对训练集中的不完美因素：首先，我们在对抗训练过程中引入一个先知模型，帮助模型学习正确的数据-标签条件分布。该精心设计的先知模型能为对抗训练提供准确的标签标注。其次，我们提出对数几率调整对抗训练方法以克服数据不平衡问题，这有助于模型学习贝叶斯最优分布。综合评估结果表明，在数据不平衡与标签噪声复杂组合的场景下，OAT相比其他基线方法实现了超过20%的干净精度提升和10%的鲁棒精度提升。代码详见https://github.com/GuanlinLee/OAT。