Cryptology ePrint Archive: Report 2019/439
A Comprehensive Study of Deep Learning for Side-Channel Analysis
Loïc Masure and Cécile Dumas and Emmanuel Prouff
Abstract: Recently, several studies have been published on the application of deep
learning to enhance Side-Channel Attacks (SCA). These seminal works have practically
validated the soundness of the approach, especially against implementations protected
by masking or by jittering. Concurrently, important open issues have emerged.
Among them, the relevance of machine (and thereby deep) learning based SCA has
been questioned in several papers based on the lack of relation between the accuracy,
a typical performance metric used in machine learning, and common SCA metrics
like the Guessing entropy or the key-discrimination success rate. Also, the impact of
the classical side-channel counter-measures on the efficiency of deep learning has been
questioned, in particular by the semi-conductor industry. Both questions enlighten
the importance of studying the theoretical soundness of deep learning in the context
of side-channel and of developing means to quantify its efficiency, especially with
respect to the optimality bounds published so far in the literature for side-channel
leakage exploitation. The first main contribution of this paper directly concerns
the latter point. It is indeed proved that minimizing the Negative Log Likelihood
(NLL for short) loss function during the training of deep neural networks is actually
asymptotically equivalent to maximizing the Perceived Information introduced by
Renauld et al. at EUROCRYPT 2011 as a lower bound of the Mutual Information
between the leakage and the target secret. Hence, such a training can be considered
as an efficient and effective estimation of the PI, and thereby of the MI (known
to be complex to accurately estimate in the context of secure implementations).
As a second direct consequence of our main contribution, it is argued that, in a
side-channel exploitation context, choosing the NLL loss function to drive the training
is sound from an information theory point of view. As a third contribution, classical
counter-measures like Boolean masking or execution flow shuffling, initially dedicated
to classical SCA, are proved to stay sound against deep Learning based attacks.
Category / Keywords: Side-Channel Analysis · Profiling Attacks · machine learning · deep learning
Original Publication (in the same form): IACR-CHES-2020
Date: received 30 Apr 2019, last revised 18 Oct 2019
Contact author: loic masure at cea fr, cecile dumas at cea fr, e prouff at gmail com
Available format(s): PDF | BibTeX Citation
Version: 20191018:085459 (All versions of this report)
Short URL: ia.cr/2019/439
[ Cryptology ePrint archive ]