Investigating Efficient Deep Learning Architectures For Side-Channel Attacks on AES
This work addresses efficiency challenges for researchers and practitioners in embedded security, but it is incremental as it builds upon existing methods.
The authors tackled the problem of reducing computational and data costs in deep learning-based side-channel attacks on AES, achieving improved performance by developing a JAX-based framework and testing Transformer-based models on the ASCAD database.
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.