Playing with blocks: Toward re-usable deep learning models for side-channel profiled attacks

TL;DR

This paper presents a modular deep learning framework for side-channel analysis that enables reusability of trained components, reducing effort and demonstrating transferability across different evaluations.

Contribution

It introduces a novel modular deep learning architecture for side-channel analysis, allowing exchangeable components to facilitate reuse and transfer learning.

Findings

Feasibility of assessing side-channel evaluations with the proposed architecture

Demonstration of transferability of learned modules across different evaluations

Reduction in development effort for new side-channel analysis models

Abstract

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.