Investigating Efficient Deep Learning Architectures For Side-Channel Attacks on AES

TL;DR

This paper explores the use of deep learning, including Transformer models, to improve side-channel attack efficiency on AES, aiming to reduce data and computational requirements.

Contribution

It introduces a JAX-based framework for deep learning in SCA and evaluates Transformer models to enhance attack performance.

Findings

Reproduced previous deep learning SCA results

Developed a new JAX-based framework for SCA

Assessed Transformer models' effectiveness in SCA

Abstract

Over the past few years, deep learning has been getting progressively more popular for the exploitation of side-channel vulnerabilities in embedded cryptographic applications, as it offers advantages in terms of the amount of attack traces required for effective key recovery. A number of effective attacks using neural networks have already been published, but reducing their cost in terms of the amount of computing resources and data required is an ever-present goal, which we pursue in this work. We focus on the ANSSI Side-Channel Attack Database (ASCAD), and produce a JAX-based framework for deep-learning-based SCA, with which we reproduce a selection of previous results and build upon them in an attempt to improve their performance. We also investigate the effectiveness of various Transformer-based models.