Playing with blocks: Toward re-usable deep learning models for side-channel profiled attacks
This is an incremental improvement for researchers in side-channel analysis, aiming to make deep learning models more reusable.
The paper tackles the problem of reducing repetitive work in side-channel profiled attacks by introducing a deep learning modular network that allows exchanging trained modules, and experiments show this architecture feasibly assesses evaluations, suggesting learning transferability is possible.
This paper introduces a deep learning modular network for side-channel analysis. Our deep learning approach features the capability to exchange part of it (modules) with others networks. We aim to introduce reusable trained modules into side-channel analysis instead of building architectures for each evaluation, reducing the body of work when conducting those. Our experiments demonstrate that our architecture feasibly assesses a side-channel evaluation suggesting that learning transferability is possible with the network we propose in this paper.