Paper 2018/1196

Gradient Visualization for General Characterization in Profiling Attacks

Loïc Masure, Cécile Dumas, and Emmanuel Prouff

Abstract

In Side-Channel Analysis (SCA), several papers have shown that neural networks could be trained to efficiently extract sensitive information from implementations running on embedded devices. This paper introduces a new tool called Gradient Visualization that aims to proceed a post-mortem information leakage characterization after the successful training of a neural network. It relies on the computation of the gradient of the loss function used during the training. The gradient is no longer computed with respect to the model parameters, but with respect to the input trace components. Thus, it can accurately highlight temporal moments where sensitive information leaks. We theoretically show that this method, based on Sensitivity Analysis, may be used to efficiently localize points of interest in the SCA context. The efficiency of the proposed method does not depend on the particular countermeasures that may be applied to the measured traces as long as the profiled neural network can still learn in presence of such difficulties. In addition, the characterization can be made for each trace individually. We verified the soundness of our proposed method on simulated data and on experimental traces from a public side-channel database. Eventually we empirically show that the Sensitivity Analysis is at least as good as state-of-the-art characterization methods, in presence (or not) of countermeasures.

Note: (12/2018) Fig.4 (right) page 12 modified (from pdf to png) to avoid printing issues(02/2019) Final version (03/2019) Acknowledgements added

Metadata
Available format(s)
PDF
Category
Implementation
Publication info
Published elsewhere. MINOR revision.Constructive Side-Channel Analysis and Secure Design - 10th International Workshop, COSADE 2019, Darmstadt, Germany, April 3-5, 2019, Proceedings
DOI
10.1007/978-3-030-16350-1_9
Keywords
Side Channel AnalysisProfiling AttacksDeep LearningPoints of InterestCharacterization
Contact author(s)
loic masure @ cea fr
History
2020-06-04: last of 4 revisions
2018-12-18: received
See all versions
Short URL
https://ia.cr/2018/1196
License
Creative Commons Attribution
CC BY

BibTeX

@misc{cryptoeprint:2018/1196,
      author = {Loïc Masure and Cécile Dumas and Emmanuel Prouff},
      title = {Gradient Visualization for General Characterization in Profiling Attacks},
      howpublished = {Cryptology ePrint Archive, Paper 2018/1196},
      year = {2018},
      doi = {10.1007/978-3-030-16350-1_9},
      note = {\url{https://eprint.iacr.org/2018/1196}},
      url = {https://eprint.iacr.org/2018/1196}
}
Note: In order to protect the privacy of readers, eprint.iacr.org does not use cookies or embedded third party content.