Paper 2024/049

CL-SCA: A Contrastive Learning Approach for Profiled Side-Channel Analysis

Annv Liu, Beijing Institute of Technology
An Wang, Beijing Institute of Technology
Shaofei Sun, Beijing Institute of Technology
Congming Wei, Beijing Institute of Technology
Yaoling Ding, Beijing Institute of Technology
Yongjuan Wang
Liehuang Zhu, Beijing Institute of Technology
Abstract

Side-channel analysis (SCA) based on machine learning, particularly neural networks, has gained considerable attention in recent years. However, previous works predominantly focus on establishing connections between labels and related profiled traces, primarily capturing label-related features while often overlooking the connections between traces of the same label. This results in the loss of some valuable information. Additionally, attack traces also contain valuable information that can be used in the training process to assist model learning. To address these issues, we propose a profiled SCA approach based on contrastive learning, named CL-SCA. This approach extracts features by emphasizing the similarities among traces, thereby improving the effectiveness of key recovery while maintaining the advantages of the original SCA approach. Through experiments on different datasets from various platforms, we demonstrate that CL-SCA significantly outperforms existing methods.

Metadata
Available format(s)
PDF
Category
Attacks and cryptanalysis
Publication info
Published elsewhere. Major revision. IEEE Transactions on Information Forensics and Security
DOI
10.1109/TIFS.2025.3570123
Keywords
Side-channel analysisContrastive learningNeural networksProfiled analysis
Contact author(s)
annvliu @ 163 com
wanganl @ bit edu cn
sfsun @ bit edu cn
weicm @ bit edu cn
dyl19 @ bit edu cn
liehuangz @ bit edu cn
History
2025-05-18: last of 2 revisions
2024-01-12: received
See all versions
Short URL
https://ia.cr/2024/049
License
Creative Commons Attribution-NonCommercial-ShareAlike
CC BY-NC-SA

BibTeX

@misc{cryptoeprint:2024/049,
      author = {Annv Liu and An Wang and Shaofei Sun and Congming Wei and Yaoling Ding and Yongjuan Wang and Liehuang Zhu},
      title = {{CL}-{SCA}: A Contrastive Learning Approach for  Profiled Side-Channel Analysis},
      howpublished = {Cryptology {ePrint} Archive, Paper 2024/049},
      year = {2024},
      doi = {10.1109/TIFS.2025.3570123},
      url = {https://eprint.iacr.org/2024/049}
}
Note: In order to protect the privacy of readers, eprint.iacr.org does not use cookies or embedded third party content.