Cryptology ePrint Archive: Report 2016/921

Breaking Cryptographic Implementations Using Deep Learning Techniques

Houssem Maghrebi and 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.

Category / Keywords: deep learning, machine learning, side channel attacks, template attack, unprotected AES implementation, masked AES implementation

Original Publication (in the same form): SPACE 2016 as an invited submission

Date: received 22 Sep 2016, last revised 24 Sep 2016

Contact author: houssem maghrebi at safrangroup com

Available format(s): PDF | BibTeX Citation

Version: 20160924:215441 (All versions of this report)

Short URL: ia.cr/2016/921

Discussion forum: Show discussion | Start new discussion


[ Cryptology ePrint archive ]