Paper 2019/1477

Kilroy was here: The First Step Towards Explainability of Neural Networks in Profiled Side-channel Analysis

Daan van der Valk and Stjepan Picek and Shivam Bhasin

Abstract

While several works have explored the application of deep learning for efficient profiled side-channel analysis, explainability or in other words what neural networks learn remains a rather untouched topic. As a first step, this paper explores the Singular Vector Canonical Correlation Analysis (SVCCA) tool to interpret what neural networks learn while training on different side-channel datasets, by concentrating on deep layers of the network. Information from SVCCA can help, to an extent, with several practical problems in a profiled side-channel analysis like portability issue and criteria to choose a number of layers/neurons to fight portability, provide insight on the correct size of training dataset and detect deceptive conditions like over-specialization of networks.