A nonprofiled side-channel analysis based on variational lower bound related to mutual information

作     者：Chi ZHANG Xiangjun LU Pei CAO Dawu GU Zheng GUO Sen XU 

作者机构：School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Zhi Xun Crypto Testing and Evaluation Technology Co. Ltd.  3. Viewsource Information Science and Technology Co. Ltd. 

出 版 物：《Science China(Information Sciences)》 (中国科学:信息科学(英文版))

年 卷 期：2023年第66卷第1期

页      面：277-295页

核心收录：

学科分类：11[军事学] 1105[军事学-军队指挥学] 0839[工学-网络空间安全] 08[工学] 110505[军事学-密码学] 110503[军事学-军事通信学] 

基　　金：supported by National Natural Science Foundation of China (Grant No. 62072307) 

主　　题：side-channel analysis nonprofiled method variational lower bound mutual information neural networks 

摘      要：In this paper, we attempt to improve the practical performance of the nonprofiled side-channel analysis(Non SCA) with the help of neural networks. We first derive a variational lower bound related to mutual information(VLBRMI) optimized for the context of Non SCA, which possesses a set of adjustable parameters and whose maximum value linearly depends on the mutual information. Then, we propose a new Non SCA method called neural mutual information analysis(NMIA) that exploits the maximum VLBRMI as the distinguisher. We present an estimator of the maximum VLBRMI, which uses neural networks to instantiate the VLBRMI and trains the neural networks to approximate the maximum VLBRMI so that we can implement the NMIA efficiently. Finally, we evaluate the NMIA on several datasets. The experimental results show that NMIA outperforms the correlation power analysis, the mutual information analysis(MIA)based on histograms, the MIA based on kernel density estimation, and the state-of-the-art Non SCA method based on neural networks.