You are looking at a specific version 20201027:121813 of this paper. See the latest version.

Paper 2020/872

Ranking Loss: Maximizing the Success Rate in Deep Learning Side-Channel Analysis

Gabriel Zaid and Lilian Bossuet and François Dassance and Amaury Habrard and Alexandre Venelli

Abstract

The side-channel community recently investigated a new approach, based on deep learning, to significantly improve profiled attacks against embedded systems. Compared to template attacks, deep learning techniques can deal with protected implementations, such as masking or desynchronization, without substantial pre-processing. However, important issues are still open. One challenging problem is to adapt the methods classically used in the machine learning field (e.g. loss function, performance metrics) to the specific side-channel context in order to obtain optimal results. We propose a new loss function derived from the learning to rank approach that helps preventing approximation and estimation errors, induced by the classical cross-entropy loss. We theoretically demonstrate that this new function, called Ranking Loss (RkL), maximizes the success rate by minimizing the ranking error of the secret key in comparison with all other hypotheses. The resulting model converges towards the optimal distinguisher when considering the mutual information between the secret and the leakage. Consequently, the approximation error is prevented. Furthermore, the estimation error, induced by the cross-entropy, is reduced by up to 23%. When the ranking loss is used, the convergence towards the best solution is up to 23% faster than a model using the cross-entropy loss function. We validate our theoretical propositions on public datasets.

Metadata
Available format(s)
PDF
Category
Secret-key cryptography
Publication info
A minor revision of an IACR publication in TCHES 2021
Contact author(s)
gabriel zaid @ univ-st-etienne fr
History
2020-10-27: revised
2020-07-12: received
See all versions
Short URL
https://ia.cr/2020/872
License
Creative Commons Attribution
CC BY
Note: In order to protect the privacy of readers, eprint.iacr.org does not use cookies or embedded third party content.