Side-channel analysis (SCA) capitalizes on unintentionally leaked information to extract sensitive data from cryptographic systems. Over recent years, deep learning has shown effectiveness in analyzing the diverse forms of SCA signals. However, due to the absence of a comprehensive understanding, constructing effective networks tailored for a variety of cryptographic systems becomes a considerable challenge. This paper proposes a novel methodology designed to deconstruct networks intended for SCA, with the goal of enhancing our understanding of the mechanisms by which these complex systems process diverse SCA signals. Our approach begins with a f-ANOVA-based method to pinpoint pivotal parameter amidst a plethora of adjustable ones. Thereafter, network visualization technique is harnessed to investigate the impact of variations in these key parameters. Through experiments, we have distilled principles for network formulation that accommodate the unique characteristics inherent in side-channel signals. The experimental outcomes highlight notable improvements when parameters are set according to the proposed principles.

Deep learning (DL)-based techniques have garnered significant attention as an innovative method for profiled side-channel analysis (SCA). Despite their proven effectiveness, recent studies have highlighted challenges faced by DL-based profiled attacks in a more realistic portability threat model, where two devices are used respectively for profiling and the attack. In this paper, we propose a novel approach for cross-device attack by incorporating the Denoising Diffusion Probabilistic Model (DDPM) to develop a generalized model. Additionally, an adaptive multi-task loss is employed to balance multiple training objectives that respectively focus on model generalization and precision. We evaluate our strategy on five cross-device SCA datasets. The experimental results show that, compared to baseline methods, our approach achieves significantly enhanced performance, as measured by the number of traces required to recover the secret key. Specifically, on a more challenging dataset obtained from three SAKURA-G evaluation boards, our method successfully recovers the secret key using approximately 300 traces, whereas baseline methods fail to guarantee a successful cross-device attack even with 5,000 traces. Furthermore, our method demonstrates remarkably enhanced attack efficiency, reducing attack time by over an hour compared to the baselines.