DL-SCADS: Deep Learning-Based Post-Silicon Side-Channel Analysis Using Decomposed Signal

Dipayan Saha; Farimah Farahmandi

Paper 2025/011

DL-SCADS: Deep Learning-Based Post-Silicon Side-Channel Analysis Using Decomposed Signal

Dipayan Saha

, University of Florida

Farimah Farahmandi, University of Florida

Abstract

Side-channel analysis (SCA) does not aim at the algorithm's weaknesses but rather its implementations. The rise of machine learning (ML) and deep learning (DL) is giving adversaries advanced capabilities to perform stealthy attacks. In this paper, we propose DL-SCADS, a DL-based approach along with signal decomposition techniques to leverage the power of secret key extraction from post-silicon EM/power side-channel traces. We integrate previously proven effective ideas of model ensembling and automated hyperparameter tuning with signal decomposition to develop an efficient and robust side-channel attack. Extensive experiments are performed on Advanced Encryption Standard (AES) and Post-Quantum Cryptography (PQC) to demonstrate the efficacy of our approach. The evaluation of the performance of the side-channel attack employing various decomposition techniques and comparison with the proposed approach in a range of datasets are also tabulated.

Note: This paper has been accepted and presented at the 58th Asilomar Conference on Signals, Systems, and Computers, 2024.

Metadata

Available format(s): PDF
Category: Attacks and cryptanalysis
Publication info: Published elsewhere. 58th Asilomar Conference on Signals, Systems, and Computers, 2024
Keywords: Side-Channel Analysis Side-Channel Attack Deep Learning Signal Decomposition
Contact author(s): dsaha @ ufl edu
farimah @ ece ufl edu
History: 2025-01-03: approved; 2025-01-02: received; See all versions
Short URL: https://ia.cr/2025/011
License: CC BY

BibTeX

@misc{cryptoeprint:2025/011,
      author = {Dipayan Saha and Farimah Farahmandi},
      title = {{DL}-{SCADS}: Deep Learning-Based Post-Silicon Side-Channel Analysis Using Decomposed Signal},
      howpublished = {Cryptology {ePrint} Archive, Paper 2025/011},
      year = {2025},
      url = {https://eprint.iacr.org/2025/011}
}