Journal of Cryptographic Engineering Computer Networks and Communications

Profiling side channel analysis with deep learning based on boosting algorithm

Yan, Longde, Chen, Aidong, Liu, Yang, Zhu, Yueying, Zhang, YanLong, Wang, Shuo, Zhou, Jing
Springer Nature · 2026-09-07 · DOI 10.1007/s13389-026-00399-7

Abstract

This paper proposes SCABoosting, a novel boosting framework for deep learning-based Side-Channel Analysis (SCA) that significantly enhances key recovery efficiency while maintaining computational lightweightness. Our method integrates multiple randomly generated CNN classifiers through a sequential boosting strategy, achieving superior performance with only 26 M parameters compared to 68 M parameters required by state-of-the-art CNNbest models. Extensive evaluation on three standard datasets demonstrates compelling results: on ASCAD dataset, our approach reduces guessing entropy (GE) to 102 (vs 204 for CNNbest) and achieves 92% success rate with 50% fewer traces; on CHES2018, GE decreases to 78 (vs 145) with 76% success rate improvement; on DPAv4, we achieve 89% success rate (vs 60% baseline) while reducing the number of required traces by 48%. These improvements are achieved without increasing training time, making SCABoosting particularly suitable for resource-constrained attack scenarios in IoT security assessment.

Read at publisher →