In recent years, many deep learning and machine learning based side channel analysis (SCA) techniques have been proposed, most of which are based on the optimization of existing network models to improve the performance of SCA. However, in practice, the attacker often captures unbalanced and small samples of data due to various environmental factors that limit and interfere with the successful implementation of SCA. To address this problem, in this paper, we firstly introduced the Conditional Generation Adversarial Network (CGAN). We proposed a new model SCA-CGAN that combines SCA and CGAN. We used it to generate a specified number and class of simulated energy traces to expand and augment the original energy traces. Finally, we used the augmented data to implement SCA and achieved a good result. Through experiments on the unprotected ChipWhisperer (CW) data and the ASCAD jittered dataset, the results shown that the SCA using the augmented data is the most efficient, and the correct key is successfully recovered on both datasets. For the CW dataset, the model accuracy is improved by 20.75% and the traces number required to recover the correct key is reduced by about 79.5%. For the ASCAD jittered dataset, when the jitter is 0 and 50, the traces number required to recover the correct key is reduced by about 76.8% and 75.7% respectively.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.