SoK: Deep Learning-based Physical Side-channel Analysis

Sengim Karayalcin; Marina Krcek; Stjepan Picek

Paper 2025/1309

SoK: Deep Learning-based Physical Side-channel Analysis

Sengim Karayalcin

, Leiden University

Marina Krcek

, Radboud University Nijmegen

Stjepan Picek

, Radboud University Nijmegen, University of Zagreb

Abstract

Deep learning-based side-channel analysis (DLSCA) represents a powerful paradigm for running side-channel attacks. DLSCA, in a state-of-the-art setting, can break multiple targets with a single attack trace, requiring minimal feature engineering. As such, DLSCA is an extremely active research area for both industry and academia. At the same time, due to domain activity, it becomes more difficult to understand the current trends and challenges. In this systematization of knowledge, we provide a critical overview of developments in DLSCA over the past years, enabling us to offer concrete suggestions and taxonomies. Moreover, we examine the reproducibility perspective and show that achieving it in full is difficult and requires a careful experimental setup.

Metadata

Available format(s): PDF
Category: Attacks and cryptanalysis
Publication info: Preprint.
Keywords: Deep Learning Side-channel Analysis Threat Model Hyperparameter Tuning Interpretability
Contact author(s): s karayalcin @ liacs leidenuniv nl
marina krcek @ ru nl
stjepan picek @ ru nl
History: 2026-06-01: last of 2 revisions; 2025-07-17: received; See all versions
Short URL: https://ia.cr/2025/1309
License: CC BY

BibTeX

@misc{cryptoeprint:2025/1309,
      author = {Sengim Karayalcin and Marina Krcek and Stjepan Picek},
      title = {{SoK}: Deep Learning-based Physical Side-channel Analysis},
      howpublished = {Cryptology {ePrint} Archive, Paper 2025/1309},
      year = {2025},
      url = {https://eprint.iacr.org/2025/1309}
}