Keep It Unsupervised: Horizontal Attacks Meet Simple Classifiers

Sana Boussam; Ninon Calleja Albillos

Paper 2025/1135

Keep It Unsupervised: Horizontal Attacks Meet Simple Classifiers

Sana Boussam, Inria Saclay - Île-de-France Research Centre, Institut Polytechnique de Paris, Thales ITSEF (France)

Ninon Calleja Albillos, CEA LETI, Grenoble Alpes University

Abstract

In the last years, Deep Learning algorithms have been browsed and applied to Side-Channel Analysis in order to enhance attack’s performances. In some cases, the proposals came without an indepth analysis allowing to understand the tool, its applicability scenarios, its limitations and the advantages it brings with respect to classical statistical tools. As an example, a study presented at CHES 2021 proposed a corrective iterative framework to perform an unsupervised attack which achieves a 100% key bits recovery. In this paper we analyze the iterative framework and the datasets it was applied onto. The analysis suggests a much easier and interpretable way to both implement such an iterative framework and perform the attack using more conventional solutions, without affecting the attack’s performances.

Metadata

Available format(s): PDF
Category: Attacks and cryptanalysis
Publication info: Published elsewhere. CARDIS 2023
DOI: 10.1007/978-3-031-54409-5_11
Keywords: Side-Channel Analysis Unsupervised Learning Non profiled attacks Deep Learning Noisy Labels Clustering
Contact author(s): sana boussam @ inria fr
ninon callejaalbillos @ cea fr
History: 2025-06-17: approved; 2025-06-16: received; See all versions
Short URL: https://ia.cr/2025/1135
License: CC BY

BibTeX

@misc{cryptoeprint:2025/1135,
      author = {Sana Boussam and Ninon Calleja Albillos},
      title = {Keep It Unsupervised: Horizontal Attacks Meet Simple Classifiers},
      howpublished = {Cryptology {ePrint} Archive, Paper 2025/1135},
      year = {2025},
      doi = {10.1007/978-3-031-54409-5_11},
      url = {https://eprint.iacr.org/2025/1135}
}