Paper 2023/1681
The Need for MORE: Unsupervised Side-channel Analysis with Single Network Training and Multi-output Regression
Abstract
Deep learning-based profiling side-channel analysis has gained widespread adoption in academia and industry due to its ability to uncover secrets protected by countermeasures. However, to exploit this capability, an adversary must have access to a clone of the targeted device to obtain profiling measurements and know secret information to label these measurements. Non-profiling attacks avoid these constraints by not relying on secret information for labeled data. Instead, they attempt all key guesses and select the most successful one. Deep learning approaches form the foundation of several non-profiling attacks, but these methods often suffer from high computational complexity and limited performance in practical applications. This work explores the performance of multi-output regression (MOR) models in side-channel analysis. We start with the recently proposed multi-output regression (MOR) approach for non-profiling side-channel analysis. Then, we significantly improve its performance by updating the 1) loss function, 2) distinguisher, and 3) employing a novel concept of validation set to reduce overfitting. We denote our approach as MORE - Multi-Output Regression Enhanced, which emphasizes significantly better attack performance than MOR. Our results demonstrate that combining the MORE methodology, ensembles, and data augmentation presents a potent strategy for enhancing non-profiling side-channel attack performance and improving the reliability of distinguishing key candidates.
Metadata
- Available format(s)
- Category
- Attacks and cryptanalysis
- Publication info
- Preprint.
- Keywords
- Side-channel AnalysisDeep learningNon-profilingRegressionData Augmentation
- Contact author(s)
-
m krcek @ tudelft nl
g perin @ liacs leidenuniv nl
lichao wu @ ru nl
stjepan picek @ ru nl - History
- 2023-11-03: approved
- 2023-10-30: received
- See all versions
- Short URL
- https://ia.cr/2023/1681
- License
-
CC BY
BibTeX
@misc{cryptoeprint:2023/1681, author = {Ioana Savu and Marina Krček and Guilherme Perin and Lichao Wu and Stjepan Picek}, title = {The Need for {MORE}: Unsupervised Side-channel Analysis with Single Network Training and Multi-output Regression}, howpublished = {Cryptology {ePrint} Archive, Paper 2023/1681}, year = {2023}, url = {https://eprint.iacr.org/2023/1681} }