EUVIMEDOpdag EUVIMED
Crossref

Unleashing Cross-Domain Potential: Side-Channel Analysis with Autoencoder for Domain Adaptation

Xiaoyu Du, Haowen Tan, Jian Shen, Pandi Vijayakumar, Sangman Moh, Q. M. Jonathan Wu

ACM Transactions on Embedded Computing Systems · 2026-05-31 · 25 (3) · 1-24

DOI: 10.1145/3800949 ↗

At a glance

Journal article in ACM Transactions on Embedded Computing Systems, published online on 2026-04-14. Written by Xiaoyu Du and 5 co-authors. 42 references. Funded by: National Key R&D Program of China, National Natural Science Foundation of China, Fundamental Research Funds of Zhejiang Sci-Tech University.

AbstractBibliografiske oplysningerCiteRelated studies

Abstract (original language)

Deep learning based side-channel analysis (DL-SCA) has achieved remarkable success in recovering cryptographic keys from embedded devices by exploiting physical leakages such as power consumption and electromagnetic emissions, posing a serious threat to the security of cryptographic implementations. However, a major challenge arises in cross-device attacks, where a model trained on profiling devices cannot be directly applied to attack a different device. This is because domain discrepancies emerge from variations in chip architecture, manufacturing, operational conditions, and data acquisition methods between these two devices. Many existing DL-SCA schemes have not adequately addressed the challenges posed by the differences. Therefore, we propose a novel cross-device SCA framework based on an autoencoder, which leverages the encoder—decoder architecture to align feature distributions across devices in the latent space while simultaneously preserving discriminative leakage features through the reconstruction process. To achieve this, Maximum Mean Discrepancy (MMD) is integrated into the loss function and applied to the latent representations, effectively narrowing the distribution gap between profiling and attack devices. Operating in the latent space allows our approach to avoid the training instability of adversarial methods and provides an efficient end-to-end solution for domain alignment. Building on this framework, we further introduce three multi-domain adaptation methods. Experimental results, evaluated in terms of Partial Guessing Entropy (PGE), demonstrate that cross-device attacks can be effectively executed even with device discrepancies, with most keys being successfully recovered within 1,000 traces. Moreover, the proposed adaptation techniques significantly reduce the number of traces required for successful key recovery.

Funding

  • National Key R&D Program of China
  • National Natural Science Foundation of China
  • Fundamental Research Funds of Zhejiang Sci-Tech University
  • Program for Leading Innovative Research Team of Zhejiang Province
  • Zhejiang Provincial Natural Science Foundation of China
  • “Pioneer” and “Leading Goose” R&D Program of Zhejiang

Cite

APA

Du, X., Tan, H., Shen, J., Vijayakumar, P., Moh, S., & Wu, Q. M. J. (2026). Unleashing Cross-Domain Potential: Side-Channel Analysis with Autoencoder for Domain Adaptation. ACM Transactions on Embedded Computing Systems, 25(3), 1-24. https://doi.org/10.1145/3800949

Vancouver

Du X, Tan H, Shen J, Vijayakumar P, Moh S, Wu QMJ. Unleashing Cross-Domain Potential: Side-Channel Analysis with Autoencoder for Domain Adaptation. ACM Transactions on Embedded Computing Systems. 2026;25(3):1-24. doi:10.1145/3800949

BibTeX
@article{Du2026,
  author = {Du, Xiaoyu and Tan, Haowen and Shen, Jian and Vijayakumar, Pandi and Moh, Sangman and Wu, Q. M. Jonathan},
  title = {Unleashing Cross-Domain Potential: Side-Channel Analysis with Autoencoder for Domain Adaptation},
  journal = {ACM Transactions on Embedded Computing Systems},
  year = {2026},
  volume = {25},
  number = {3},
  pages = {1--24},
  doi = {10.1145/3800949}
}
Start for free →