Recent developments in neural architecture search (NAS) emphasize the significance of considering robust architectures against malicious data. However, there is a notable absence of benchmark evaluations and theoretical guarantees for searching these robust architectures, especially when adversarial training is considered. In this work, we aim to address these two challenges, making twofold contributions. First, we release a comprehensive data set that encompasses both clean accuracy and robust accuracy for a vast array of adversarially trained networks from the NAS-Bench-201 search space on image datasets. Then, leveraging the neural tangent kernel (NTK) tool from deep learning theory, we establish a generalization theory for searching architecture in terms of clean accuracy and robust accuracy under multi-objective adversarial training. We firmly believe that our benchmark and theoretical insights will significantly benefit the NAS community through reliable reproducibility, efficient assessment, and theoretical foundation, particularly in the pursuit of robust architectures.

最近神经网络架构搜索(NAS)的发展强调考虑恶意数据下的鲁棒性架构的重要性，然而，在搜索这些鲁棒性架构时，尤其是在考虑对抗训练时，缺乏显著的基准评估和理论保证。本文旨在解决这两个挑战，做出了双重贡献：首先，我们发布了一个综合数据集，该数据集包含来自NAS-Bench-201搜索空间在图像数据集上经过对抗训练的网络的干净准确度和鲁棒准确度；其次，利用深度学习理论中的神经切线核(NTK)工具，我们建立了一个关于在干净准确度和鲁棒准确度下搜索架构的泛化理论，该理论适用于多目标对抗训练。我们坚信，我们的基准和理论见解将对NAS社区产生重大影响，通过可靠的再现性、高效的评估和理论基础，特别是在追求鲁棒架构方面。

鲁棒性对抗训练下的NAS：基准、理论与进展