On the Performance of Convolutional Neural Networks for Side-Channel Analysis

Stjepan Picek, Ioannis Petros Samiotis, Jeahun Kim, Annelie Heuser, Shivam Bhasin, Axel Legay

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

66 Citations (Scopus)

Abstract

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
PublisherSpringer
Pages157-176
Number of pages20
ISBN (Electronic)978-3-030-05072-6
ISBN (Print)978-3-030-05071-9
DOIs
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
PublisherSpringer
Volume11348
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

ConferenceSPACE 2018: International Conference on Security, Privacy, and Applied Cryptography Engineering
Country/TerritoryIndia
CityKanpur
Period15/12/1819/12/18

Keywords

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

Fingerprint

Dive into the research topics of 'On the Performance of Convolutional Neural Networks for Side-Channel Analysis'. Together they form a unique fingerprint.

Cite this