Paper 2021/952

On the Evaluation of Deep Learning-based Side-channel Analysis

Lichao Wu, Guilherme Perin, and Stjepan Picek

Abstract

Deep learning-based side-channel analysis already became a de-facto standard when investigating the most powerful profiling side-channel analysis. The results from the last few years show that deep learning techniques can efficiently break targets that are even protected with countermeasures. While there are constant improvements in making the deep learning-based attacks more powerful, little is done on evaluating such attacks' performance. Indeed, what is done today is not different from what was done more than a decade ago. This paper considers how to evaluate deep learning-based side-channel analysis and whether the commonly used techniques give the best results. To that end, we consider different summary statistics and the influence of algorithmic randomness on the stability of profiling models. Our results show that besides commonly used metrics like guessing entropy, one should also show the standard deviation results to assess the attack performance properly. Our results show that using the arithmetic mean for guessing entropy does not yield the best results, and instead, a geometric mean should be used.