Mixup Data Augmentation for Deep Learning Side-Channel Attacks

Karim M. Abdellatif

Abstract

Following the current direction in Deep Learning (DL), more recent papers have started to pay attention to the efficiency of DL in breaking cryptographic implementations. Several works focus on techniques to boost the efficiency of existing architectures by data augmentation, regularization, etc. In this work, we investigate using mixup data augmentation \cite{zhang2017mixup} in order to improve the efficiency of DL-based Side-Channel Attacks (SCAs). We validated the soundness of the mixup on real traces collected from the ChipWhisperer board \cite{cw} and from the ASCAD database \cite{benadjila2020deep}. The obtained results have proven that using mixup data augmentation decreases the number of measurements needed to reveal the secret key compared to the non-augmented case.

Available format(s)
Publication info
Preprint. Minor revision.
Keywords
Deep LearningSide-Channel AttacksData AugmentationMixup and AES
Contact author(s)
karim m abdellatif @ gmail com
History
Short URL
https://ia.cr/2021/328

CC BY

BibTeX

@misc{cryptoeprint:2021/328,
author = {Karim M.  Abdellatif},
title = {Mixup Data Augmentation for Deep Learning Side-Channel Attacks},
howpublished = {Cryptology ePrint Archive, Paper 2021/328},
year = {2021},
note = {\url{https://eprint.iacr.org/2021/328}},
url = {https://eprint.iacr.org/2021/328}
}

Note: In order to protect the privacy of readers, eprint.iacr.org does not use cookies or embedded third party content.