In this work, we ask a question whether Convolutional Neural Networks are more suitable for side-channel attacks than some other machine learning techniques and if yes, in what situations. Our results point that Convolutional Neural Networks indeed outperform machine learning in several scenarios when considering accuracy. Still, often there is no compelling reason to use such a complex technique. In fact, if comparing techniques without extra steps like preprocessing, we see an obvious advantage for Convolutional Neural Networks when the level of noise is small, and the number of measurements and features is high. The other tested settings show that simpler machine learning techniques, for a significantly lower computational cost, perform similarly or sometimes even better. The experiments with guessing entropy indicate that methods like Random Forest or XGBoost could perform better than Convolutional Neural Networks for the datasets we investigated.
Original languageEnglish
Title of host publicationSecurity, Privacy, and Applied Cryptography Engineering
Subtitle of host publication8th International Conference, SPACE 2018, Kanpur, India, December 15-19, 2018, Proceedings
EditorsA. Chattopadhyay, C. Rebeiro, Y. Yarom
Place of PublicationCham
Number of pages20
ISBN (Electronic)978-3-030-05072-6
ISBN (Print)978-3-030-05071-9
Publication statusPublished - 2018
EventSPACE 2018: International Conference on Security, Privacy, and Applied Cryptography Engineering : 8th International Conference - Kanpur, India
Duration: 15 Dec 201819 Dec 2018
Conference number: 8th

Publication series

NameLecture Notes in Computer Science
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349


ConferenceSPACE 2018: International Conference on Security, Privacy, and Applied Cryptography Engineering

    Research areas

  • Side-channel analysis, Machine learning, Deep learning , Convolutional Neural Networks

ID: 47775139