Adversarial parameter defense by multi-step risk minimization. (December 2021)

• Record Type: Journal Article
• Authors: Zhang, Zhiyuan; Luo, Ruixuan; Ren, Xuancheng; Su, Qi; Li, Liangyou; Sun, Xu
• Is Part Of: Neural networks. Volume 144(2021)
• Page Start: 154
• Page End: 163
• Publication Date: 2021-12
• Subjects: Vulnerability of deep neural networks -- Parameter corruption -- Adversarial parameter defense; Neural computers -- Periodicals; Neural networks (Computer science) -- Periodicals; Neural networks (Neurobiology) -- Periodicals; Nervous System -- Periodicals; Ordinateurs neuronaux -- Périodiques; Réseaux neuronaux (Informatique) -- Périodiques; Réseaux neuronaux (Neurobiologie) -- Périodiques; Neural computers; Neural networks (Computer science); Neural networks (Neurobiology); Periodicals; 006.32
• DOI: 10.1016/j.neunet.2021.08.022
• Languages: English
• ISSNs: 0893-6080

Abstract

Abstract: Previous studies demonstrate DNNs' vulnerability to adversarial examples and adversarial training can establish a defense to adversarial examples. In addition, recent studies show that deep neural networks also exhibit vulnerability to parameter corruptions. The vulnerability of model parameters is of crucial value to the study of model robustness and generalization. In this work, we introduce the concept of parameter corruption and propose to leverage the loss change indicators for measuring the flatness of the loss basin and the parameter robustness of neural network parameters. On such basis, we analyze parameter corruptions and propose the multi-step adversarial corruption algorithm. To enhance neural networks, we propose the adversarial parameter defense algorithm that minimizes the average risk of multiple adversarial parameter corruptions. Experimental results show that the proposed algorithm can improve both the parameter robustness and accuracy of neural networks.