Train or Adapt a Deeply Learned Profile? - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Train or Adapt a Deeply Learned Profile?

Résumé

In recent years, many papers have shown that deep learning can be beneficial for profiled side-channel analysis. However, to obtain good performance with deep learning, an evaluator or an attacker face the issue of data. Due to the context, he might be limited in the amount of data for training. This can be mitigated with classical Machine Learning (ML) techniques such as data augmentation. However, these mitigation techniques lead to a significant increase in the training time; first, by augmenting the data and second, by increasing the time to perform the learning of the neural network. Recently, weight initialization techniques using specific probability distributions have shown some impact on the training performances in sidechannel analysis. In this work, we investigate the advantage of using weights initialized from a previous training of a network in some different contexts. The idea behind this is that different side-channel attacks share common points in the sense that part of the network has to understand the link between power/electromagnetic signals and the corresponding intermediate variable. This approach is known as Transfer Learning (TL) in the Deep Learning (DL) literature and has shown its usefulness in various domains. We present various experiments showing the relevance and advantage of starting with a pretrained model In our scenarios, pretrained models are trained on different probe positions/channels/chips. Using TL, we obtain better accuracy and/or training speed for a fixed amount of training data from the target device.
Fichier principal
Vignette du fichier
YACCRYPTED_2020_Extended (6).pdf (3.86 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03458681 , version 1 (02-02-2022)

Identifiants

Citer

Christophe Genevey-Metat, Annelie Heuser, Gerard Benoit. Train or Adapt a Deeply Learned Profile?. LATINCRYPT 2021 - 7th International Conference on Cryptology and Information Security in Latin America, Oct 2021, Bogota, Colombia. ⟨10.1007/978-3-030-88238-9_11⟩. ⟨hal-03458681⟩
22 Consultations
51 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More