Keep It Unbiased: A Comparison Between Estimation of Distribution Algorithms and Deep Learning for Human Interaction-Free Side-Channel Analysis

TL;DR

This paper compares estimation of distribution algorithms and deep learning for human interaction-free side-channel analysis, highlighting their effectiveness and complexity in security evaluations through experimental results.

Contribution

It provides a comparative analysis of EDAs and deep learning methods for side-channel analysis, emphasizing their advantages and limitations.

Findings

EDAs can mitigate human dependency without added complexity

Deep learning simplifies attack procedures but requires complex neural networks

Experimental results show varying effectiveness depending on datasets

Abstract

Evaluating side-channel analysis (SCA) security is a complex process, involving applying several techniques whose success depends on human engineering. Therefore, it is crucial to avoid a false sense of confidence provided by non-optimal (failing) attacks. Different alternatives have emerged lately trying to mitigate human dependency, among which deep learning (DL) attacks are the most studied today. DL promise to simplify the procedure by e.g. evading the need for point of interest selection or the capability of bypassing noise and desynchronization, among other shortcuts. However, including DL in the equation comes at a price, since working with neural networks is not straightforward in this context. Recently, an alternative has appeared with the potential to mitigate this dependence without adding extra complexity: Estimation of Distribution Algorithm-based SCA. In this paper, we compare these two relevant methods, supporting our findings by experiments on various datasets.