Improving machine learning based side-channel analysis: can dropout be dropped out?

Improving machine learning based side-channel analysis: can dropout be dropped out?

Kok, Jim (TU Delft Electrical Engineering, Mathematics and Computer Science)

Picek, S. (mentor)
Krcek, M. (mentor)

Delft University of Technology

Computer Science and Engineering

CSE3000 Research Project

2020-06-22

Analysing physical leakages (e.g. power consumption and electromagnetic radiation) of cryptographic devices can be used by adversaries to extract secret keys. Over the last couple of years, researchers have shown that machine learning has potential for this process. Machine learning models need to be fine-tuned to enhance key extraction performance. This paper investigates the so-called dropout hyper-parameter, which is proven to reduce overfitting in various domains (e.g. speech recognition). Dropout is examined for two different models: multilayer perceptrons and convolutional neural networks. Regarding the convolutional neural networks, two architectures are examined: one architecture used as a benchmark in various papers and a more uncomplicated one. The findings of this paper showed that adding dropout to the investigated multilayer perceptron architecture led to significant improvements, whereas the convolutional neural network architectures showed negligible improvements.

Side-channel analysis
machine learning
overfitting
dropout

http://resolver.tudelft.nl/uuid:3391941a-6910-436e-98c5-c7c5b6ddd4fd

Student theses

bachelor thesis

© 2020 Jim Kok