Paper 2016/921

Breaking Cryptographic Implementations Using Deep Learning Techniques

Houssem Maghrebi, Thibault Portigliatti, and Emmanuel Prouff

Abstract

Template attack is the most common and powerful profiled side channel attack. It relies on a realistic assumption regarding the noise of the device under attack: the probability density function of the data is a multivariate Gaussian distribution. To relax this assumption, a recent line of research has investigated new profiling approaches mainly by applying machine learning techniques. The obtained results are commensurate, and in some particular cases better, compared to template attack. In this work, we propose to continue this recent line of research by applying more sophisticated profiling techniques based on deep learning. Our experimental results confirm the overwhelming advantages of the resulting new attacks when targeting both unprotected and protected cryptographic implementations.

Metadata
Available format(s)
PDF
Publication info
Published elsewhere. SPACE 2016 as an invited submission
Keywords
deep learningmachine learningside channel attackstemplate attackunprotected AES implementationmasked AES implementation
Contact author(s)
houssem maghrebi @ safrangroup com
History
2016-09-24: received
Short URL
https://ia.cr/2016/921
License
Creative Commons Attribution
CC BY

BibTeX

@misc{cryptoeprint:2016/921,
      author = {Houssem Maghrebi and Thibault Portigliatti and Emmanuel Prouff},
      title = {Breaking Cryptographic Implementations Using Deep Learning Techniques},
      howpublished = {Cryptology ePrint Archive, Paper 2016/921},
      year = {2016},
      note = {\url{https://eprint.iacr.org/2016/921}},
      url = {https://eprint.iacr.org/2016/921}
}
Note: In order to protect the privacy of readers, eprint.iacr.org does not use cookies or embedded third party content.