Online Performance Evaluation of Deep Learning Networks for Profiled Side-Channel Analysis - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2020

Online Performance Evaluation of Deep Learning Networks for Profiled Side-Channel Analysis

Résumé

Deep learning based side-channel analysis has seen a rise in popularity over the last few years. A lot of work is done to understand the inner workings of the neural networks used to perform the attacks and a lot is still left to do. However, finding a metric suitable for evaluating the capacity of the neural networks is an open problem that is discussed in many articles. We propose an answer to this problem by introducing an online evaluation metric dedicated to the context of side-channel analysis and use it to perform early stopping on existing convolutional neural networks found in the literature. This metric compares the performance of a network on the training set and on the validation set to detect underfitting and overfitting. Consequently, we improve the performance of the networks by finding their best training epoch and thus reduce the number of traces used by 30%. The training time is also reduced for most of the networks considered.
Fichier principal
Vignette du fichier
Article final COSADE.pdf (890.24 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02937872 , version 1 (14-09-2020)

Identifiants

  • HAL Id : hal-02937872 , version 1

Citer

Damien Robissout, Gabriel Zaid, Brice Colombier, Lilian Bossuet, Amaury Habrard. Online Performance Evaluation of Deep Learning Networks for Profiled Side-Channel Analysis. International Workshop on Constructive Side-Channel Analysis and Secure Design (COSADE), Oct 2020, Lugano ( virtual ), Switzerland. ⟨hal-02937872⟩
68 Consultations
134 Téléchargements

Partager

Gmail Facebook X LinkedIn More