Neural Architectures Search (NAS) becomes more and more popular over these years. However, NAS-generated models tends to suffer greater vulnerability to various malicious attacks. Lots of robust NAS methods leverage adversarial training to enhance the robustness of NAS-generated models, however, they neglected the nature accuracy of NAS-generated models. In our paper, we propose a novel NAS method, Robust Neural Architecture Search (RNAS). To design a regularization term to balance accuracy and robustness, RNAS generates architectures with both high accuracy and good robustness. To reduce search cost, we further propose to use noise examples instead adversarial examples as input to search architectures. Extensive experiments show that RNAS achieves state-of-the-art (SOTA) performance on both image classification and adversarial attacks, which illustrates the proposed RNAS achieves a good tradeoff between robustness and accuracy.

翻译：神经架构搜索（Neural Architecture Search, NAS）近年来日益流行。然而，NAS生成的模型往往更容易遭受各类恶意攻击。许多鲁棒NAS方法利用对抗训练来增强NAS生成模型的鲁棒性，但却忽略了NAS生成模型的自然准确率。在本文中，我们提出了一种新的NAS方法——鲁棒神经架构搜索（RNAS）。通过设计一个正则化项来平衡准确率与鲁棒性，RNAS能够生成同时具备高准确率与良好鲁棒性的架构。为进一步降低搜索成本，我们提出使用噪声样本而非对抗样本作为架构搜索的输入。大量实验表明，RNAS在图像分类和对抗攻击任务上均达到了当前最优（SOTA）性能，这表明所提出的RNAS在鲁棒性与准确率之间实现了良好的权衡。