Autoencoder-enabled model portability for reducing hyperparameter tuning efforts in side-channel analysis

• Published in: Journal of cryptographic engineering 2024-09, Vol.14 (3), p.475-497
• Main Authors: Krček, Marina, Perin, Guilherme
• Format: Article
• Language: English
• Subjects: Circuits and Systems; Coding; Communications Engineering; Computer Communication Networks; Computer Science; Cryptology; Data search; Data Structures and Information Theory; Datasets; Deep learning; Depth profiling; Machine learning; Networks; Operating Systems; Portability; Regular Paper; Tuning
• ISSN: 2190-8508; 2190-8516
• DOI: 10.1007/s13389-023-00330-4

Hyperparameter tuning represents one of the main challenges in deep learning-based profiling side-channel analysis. For each different side-channel dataset, the typical procedure to find a profiling model is applying hyperparameter tuning from scratch. The main reason is that side-channel measurements from various targets contain different underlying leakage distributions. Consequently, the same profiling model hyperparameters are usually not equally efficient for other targets. This paper considers autoencoders for dimensionality reduction to verify if encoded datasets from different targets enable the portability of profiling models and architectures. Successful portability reduces the hyperparameter tuning efforts as profiling model tuning is eliminated for the new dataset, and tuning autoencoders is simpler. We first search for the best autoencoder for each dataset and the best profiling model when the encoded dataset becomes the training set. Our results show no significant difference in tuning efforts using original and encoded traces, meaning that encoded data reliably represents the original data. Next, we verify how portable is the best profiling model among different datasets. Our results show that tuning autoencoders enables and improves portability while reducing the effort in hyperparameter search for profiling models. Lastly, we present a transfer learning case where dimensionality reduction might be necessary if the model is tuned for a dataset with fewer features than the new dataset. In this case, tuning of the profiling model is eliminated and training time reduced.