Cryptology ePrint Archive: Report 2017/1110

On the Relevance of Feature Selection for Profiled Side-channel Attacks

Stjepan Picek and Annelie Heuser and Alan Jovic and Axel Legay

Abstract: In the process of profiled side-channel analysis there is a number of steps one needs to make. One important step that is often conducted without a proper attention is selection of the points of interest (features) within the side-channel measurement trace. Most of the related work start with an assumption that the features are selected and various attacks are then considered and compared to find the best approach. In this paper, we concentrate on the feature selection step and show that if a proper selection is done, most of the attack techniques offer satisfactory results. We investigate how more advanced feature selection techniques stemming from the machine learning domain can be used to improve the side-channel attack efficiency. Our results show that the so-called Hybrid feature selection methods result in the best classification accuracy over a wide range of test scenarios and number of features selected.

Category / Keywords: implementation / Profiled side-channel attacks, feature selection, machine learning, L1 regularization

Date: received 14 Nov 2017

Contact author: annelie heuser at irisa fr

Available format(s): PDF | BibTeX Citation

Version: 20171120:142347 (All versions of this report)

Short URL: ia.cr/2017/1110

Discussion forum: Show discussion | Start new discussion


[ Cryptology ePrint archive ]