Deep Neural Networks are susceptible to adversarial perturbations. Adversarial training and adversarial purification are among the most widely recognized defense strategies. Although these methods have different underlying logic, both rely on absolute logit values to generate label predictions. In this study, we theoretically analyze the logit difference around successful adversarial attacks from a theoretical point of view and propose a new principle, namely Adversarial Logit Update (ALU), to infer adversarial sample's labels. Based on ALU, we introduce a new classification paradigm that utilizes pre- and post-purification logit differences for model's adversarial robustness boost. Without requiring adversarial or additional data for model training, our clean data synthesis model can be easily applied to various pre-trained models for both adversarial sample detection and ALU-based data classification. Extensive experiments on both CIFAR-10, CIFAR-100, and tiny-ImageNet datasets show that even with simple components, the proposed solution achieves superior robustness performance compared to state-of-the-art methods against a wide range of adversarial attacks. Our python implementation is submitted in our Supplementary document and will be published upon the paper's acceptance.

在这项研究中，从理论的角度分析了成功的对抗攻击周围的逻辑差异，并提出了一种新的原则，即Adversarial Logit Update (ALU)，用于推断对抗样本的标签。基于ALU，引入了一种新的分类范式，利用预净化和后净化的逻辑差异来提高模型的对抗鲁棒性。经过广泛实验证明，所提出的解决方案在CIFAR-10、CIFAR-100和tiny-ImageNet数据集上相对于最先进的方法具有卓越的鲁棒性能。

通过对抗性输出日志更新推进对抗鲁棒性