On the Performance of Convolutional Neural Networks for Side-channel Analysis - Archive ouverte HAL Access content directly
Conference Papers Year :

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

(1) , (1) , (2) , (1) , (3) , (4)
1
2
3
4

Abstract

In this paper, we ask a question whether convolutional neural networks are more suitable for SCA scenarios than some other machine learning techniques, and if yes, in what situations. Our results point that convolutional neural networks indeed outperforms 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 only 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 similar or even better. The experiments with the guessing entropy metric indicate that simpler methods like Random forest or XGBoost perform better than convolu-tional neural networks for the datasets we investigated. Finally, we conduct a small experiment that opens the question whether convolutional neural networks are actually the best choice in side-channel analysis context since there seems to be no advantage in preserving the topology of measurements.
Fichier principal
Vignette du fichier
2018-004.pdf (597.2 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-02010591 , version 1 (07-02-2019)

Identifiers

  • HAL Id : hal-02010591 , version 1

Cite

Stjepan Picek, Ioannis Petros Samiotis, Annelie Heuser, Jaehun Kim, Shivam Bhasin, et al.. On the Performance of Convolutional Neural Networks for Side-channel Analysis. SPACE 2018 - International Conference on Security, Privacy, and Applied Cryptography Engineering, Dec 2018, Kanpur, India. pp.157-176. ⟨hal-02010591⟩
120 View
501 Download

Share

Gmail Facebook Twitter LinkedIn More