Regularizers to the Rescue: Fighting Overfitting in DeepLearning-based Side-channel Analysis
Preprint
- 21 December 2022
- preprint
- Published by Springer Nature in Research Square
Abstract
Despite considerable achievements of deep learning-based side-channel analysis, overfitting represents a significant obstacle in finding optimized neural network models. This issue is not unique to the side-channel domain. Regularization techniques are popular solutions to overfitting and have long been used in various domains. At the same time, the works in the side-channel domain show sporadic utilization of regularization techniques. What is more, no systematic study investigates these techniques’ effectiveness. In this paper, we aim to investigate the regularization effectiveness by applying four powerful and easy-to-use regularization techniques to six combinations of datasets, leakage models, and deep-learning topologies. The investigated techniques are L1, L2, dropout, and early stopping. Our results show that while all these techniques can improve performance in many cases, L1 and L2 are the most effective. Finally, if training time matters, early stopping is the best technique to choose.Keywords
All Related Versions
This publication has 8 references indexed in Scilit:
- SoK: Deep Learning-based Physical Side-channel AnalysisACM Computing Surveys, 2023
- Reinforcement Learning for Hyperparameter Tuning in Deep Learning-based Side-channel AnalysisIACR Transactions on Cryptographic Hardware and Embedded Systems, 2021
- Strength in Numbers: Improving Generalization with Ensembles in Machine Learning-based Profiled Side-channel AnalysisIACR Transactions on Cryptographic Hardware and Embedded Systems, 2020
- Dropout vs. batch normalization: an empirical study of their impact to deep learningMultimedia Tools and Applications, 2020
- Methodology for Efficient CNN Architectures in Profiling AttacksIACR Transactions on Cryptographic Hardware and Embedded Systems, 2019
- A Comprehensive Study of Deep Learning for Side-Channel AnalysisIACR Transactions on Cryptographic Hardware and Embedded Systems, 2019
- Make Some Noise. Unleashing the Power of Convolutional Neural Networks for Profiled Side-channel AnalysisIACR Transactions on Cryptographic Hardware and Embedded Systems, 2019
- ElectroMagnetic Analysis (EMA): Measures and Counter-measures for Smart Cards2001