A Literature Study into Hyperparameter Systematization for Deep Learning-based Side-Channel Analysis

Bachelor thesis (2020)

Authors

D. Mulder Electrical Engineering, Mathematics and Computer Science

Contributors

S. Picek Cyber Security - EEMCS (mentor)
M. Krcek Cyber Security - EEMCS (graduation committee member)
Faculty
Electrical Engineering, Mathematics and Computer Science, Electrical Engineering, Mathematics and Computer Science
Copyright: © 2020 Doreen Mulder
More Info
expand_more

Published Date

21-06-2020

Language

English

Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Faculty

Electrical Engineering, Mathematics and Computer Science

Abstract

With the recent increase in computational power, deep learning is being applied in many different fields. Deep learning has produced promising results in the field of side-channel analysis. However, the algorithms used to construct deep neural networks remain black boxes, which makes it hard to fully employ the capabilities of attacks performed with these techniques.
This study explores methods to systematize the deep learning techniques used in profiled side-channel analysis. We do so by conducting a literature review of the state-of-the-art. Our observations show that while the process of choosing an architecture and hyperparameters have a great influence on the performance of an attack, not all authors thoroughly document this process. In lights of further improvement of the state-of-the-art, we also propose several promising techniques for hyperparameter optimization in side-channel analysis.