Cryptology ePrint Archive: Report 2021/357

AISY - Deep Learning-based Framework for Side-channel Analysis

Guilherme Perin and Lichao Wu and Stjepan Picek

Abstract: The deep learning-based side-channel analysis represents an active research domain. While it is clear that deep learning enables powerful side-channel attacks, the variety of research scenarios often makes the results difficult to reproduce.

In this paper, we present AISY - a deep learning-based framework for profiling side-channel analysis. Our framework enables the users to run the analyses and report the results efficiently while maintaining the results' reproducible nature. The framework implements numerous features allowing state-of-the-art deep learning-based analysis. At the same time, the AISY framework allows easy add-ons of user-custom functionalities.

Category / Keywords: Side-channel Analysis, Deep Learning, Framework

Date: received 17 Mar 2021, last revised 18 Mar 2021

Contact author: picek stjepan at gmail com, g perin@gmail com, l wu-4@tudelft nl

Available format(s): PDF | BibTeX Citation

Version: 20210318:112808 (All versions of this report)

Short URL: ia.cr/2021/357


[ Cryptology ePrint archive ]