Title: Power analysis attack: an approach based on machine learning

Authors: Liran Lerman; Gianluca Bontempi; Olivier Markowitch

Addresses: Quality and Security of Information Systems and Machine Learning Group, Department of Computer Science, Université Libre de Bruxelles (ULB), Boulevard du Triomphe – CP 212, 1050 Brussels, Belgium ' Machine Learning Group, Department of Computer Science, Université Libre de Bruxelles (ULB), Boulevard du Triomphe – CP 212, 1050 Brussels, Belgium ' Quality and Security of Information Systems, Department of Computer Science, Université Libre de Bruxelles (ULB), Boulevard du Triomphe – CP 212, 1050 Brussels, Belgium

Abstract: In cryptography, a side-channel attack is any attack based on the analysis of measurements related to the physical implementation of a cryptosystem. Nowadays, the possibility of collecting a large amount of observations paves the way to the adoption of machine learning techniques, i.e., techniques able to extract information and patterns from large datasets. The use of statistical techniques for side-channel attacks is not new. Techniques like the template attack have shown their effectiveness in recent years. However, these techniques rely on parametric assumptions and are often limited to small dimensionality settings, which limit their range of application. This paper explores the use of machine learning techniques to relax such assumptions and to deal with high dimensional feature vectors.

Keywords: cryptanalysis; side-channel attacks; template attacks; machine learning; power analysis attacks; cryptography; high dimensional feature vectors; security.

DOI: 10.1504/IJACT.2014.062722

International Journal of Applied Cryptography, 2014 Vol.3 No.2, pp.97 - 115

Available online: 12 Jun 2014 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article