arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2009.00902cs.CV
收藏

逆向鲁棒神经架构

Adversarially Robust Neural Architectures

University of Sydney(悉尼大学)

Minjing Dong, Yanxi Li, Yunhe Wang, Chang Xu

摘要:

深度神经网络(DNN)容易受到对抗攻击的攻击。现有方法致力于开发各种鲁棒训练策略或正则化以更新神经网络的权重。但除了权重之外,网络中的整体结构和信息流是由神经架构明确决定的,而神经架构尚未被探索。因此,本文的目的是从体系结构的角度来提高网络的对抗鲁棒性。我们探讨了对抗鲁棒性,Lipschitz常数和结构参数之间的关系,并表明适当的约束结构参数可以减少Lipschitz常数,以进一步提高鲁棒性。架构参数的重要性可能因操作或连接而异。我们通过一个单变量对数正态分布来近似整个网络的Lipschitz常数,其均值和方差与结构参数有关。置信度可以通过基于累积函数对分布参数制定约束来实现。与各种NAS算法搜索的对抗训练的神经架构以及高效的人工设计模型相比,我们的算法在不同数据集的各种攻击下凭经验在所有模型中实现了最佳性能。

英文摘要:

Deep Neural Networks (DNNs) are vulnerable to adversarial attacks. Existing methods are devoted to developing various robust training strategies or regularizations to update the weights of the neural network. But beyond the weights, the overall structure and information flow in the network are explicitly determined by the neural architecture, which remains unexplored. This paper thus aims to improve the adversarial robustness of the network from the architecture perspective. We explore the relationship among adversarial robustness, Lipschitz constant, and architecture parameters and show that an appropriate constraint on architecture parameters could reduce the Lipschitz constant to further improve the robustness. The importance of architecture parameters could vary from operation to operation or connection to connection. We approximate the Lipschitz constant of the entire network through a univariate log-normal distribution, whose mean and variance are related to architecture parameters. The confidence can be fulfilled through formulating a constraint on the distribution parameters based on the cumulative function. Compared with adversarially trained neural architectures searched by various NAS algorithms as well as efficient human-designed models, our algorithm empirically achieves the best performance among all the models under various attacks on different datasets.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑