文献类型：期刊文献

英文题名：Unsupervised side-channel power analysis based on invariant information clustering

作者：Yang, Ning[1]; Yan, Long-De[1]; Liu, Bi-Yang[2]; Li, Xiang[3]; Chen, Ai-Dong[2]; Zeng, Lu[1]; Liu, Wei-Feng[3]

第一作者：Yang, Ning

机构：[1] Beijing Key Laboratory of Information Service Engineering, Beijing Union University, Beijing, 100101, China; [2] College of Robotics, Beijing Union University, Beijing, 100101, China; [3] Institute of Semiconductors, Chinese Academy of Sciences, Beijing, 100085, China

第一机构：北京联合大学北京市信息服务工程重点实验室

通讯机构：[2]College of Robotics, Beijing Union University, Beijing, 100101, China|[1141739]北京联合大学机器人学院;[11417]北京联合大学;

年份：2025

卷号：23

期号：4

外文期刊名：Journal of Electronic Science and Technology

收录：EI(收录号：20254519467240);Scopus(收录号：2-s2.0-105020930083)

语种：英文

外文关键词：Cluster analysis - Clustering algorithms - Cost benefit analysis - Deep learning - Extraction - Information leakage - Labeled data - Learning systems - Side channel attack

摘要：Side-channel analysis (SCA) has emerged as a research hotspot in the field of cryptanalysis. Among various approaches, unsupervised deep learning-based methods demonstrate powerful information extraction capabilities without requiring labeled data. However, existing unsupervised methods, particularly those represented by differential deep learning analysis (DDLA) and its improved variants, while overcoming the dependency on labeled data inherent in template analysis, still suffer from high time complexity and training costs when handling key byte difference comparisons. To address this issue, this paper introduces invariant information clustering (IIC) into SCA for the first time, and thus proposes a novel unsupervised learning-based SCA method, named IIC-SCA. By leveraging mutual information maximization techniques for automatic feature extraction of power leakage data, our approach achieves key recovery through a single training session, eliminating the prohibitive computational overhead of traditional methods that require separate training for all possible key bytes. Experimental results on the ASCAD dataset demonstrate successful key extraction using only 50000 training traces and 2000 attack traces. Furthermore, compared with DDLA, the proposed method reduces training time by approximately 93.40?% and memory consumption by about 6.15%, significantly decreasing the temporal and resource costs of unsupervised SCA. This breakthrough provides new insights for developing low-cost, high-efficiency cryptographic attack methodologies. ? 2025 The Authors.