Regularizers to the rescue: fighting overfitting in deep learning-based side-channel analysis

• Published in: Journal of cryptographic engineering Vol. 14; no. 4; pp. 609 - 629
• Main Authors: Rezaeezade, Azade, Batina, Lejla
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.11.2024
• Subjects: Circuits and Systems; Communications Engineering; Computer Communication Networks; Computer Science; Cryptology; Data Structures and Information Theory; Networks; Operating Systems; Research Article; Deep learning; ASCON; Side-channel analysis; Regularization; Overfitting; AES
• ISSN: 2190-8508; 2190-8516
• DOI: 10.1007/s13389-024-00361-5

Despite considerable achievements of deep learning-based side-channel analysis, overfitting represents a significant obstacle in finding optimized neural network models. This issue is not unique to the side-channel domain. Regularization techniques are popular solutions to overfitting and have long been used in various domains. At the same time, the works in the side-channel domain show sporadic utilization of regularization techniques. What is more, no systematic study investigates these techniques’ effectiveness. In this paper, we aim to investigate the regularization effectiveness on a randomly selected model, by applying 4 powerful and easy-to-use regularization techniques to 8 combinations of datasets, leakage models, and deep learning topologies. The investigated techniques are L 1 , L 2 , dropout, and early stopping. Our results show that while all these techniques can improve performance in many cases, L 1 and L 2 are the most effective. Finally, if training time matters, early stopping is the best technique.