Research Article
Combined VMD-GSO Based Points of Interest Selection Method for Profiled Side Channel Attacks
@INPROCEEDINGS{10.1007/978-3-030-77424-0_38, author={Ngoc Quy Tran and Hong Quang Nguyen and Van-Phuc Hoang}, title={Combined VMD-GSO Based Points of Interest Selection Method for Profiled Side Channel Attacks}, proceedings={Industrial Networks and Intelligent Systems. 7th EAI International Conference, INISCOM 2021, Hanoi, Vietnam, April 22-23, 2021, Proceedings}, proceedings_a={INISCOM}, year={2021}, month={5}, keywords={Profiled attack Side channel attack Support machine learning Variational mode decomposition}, doi={10.1007/978-3-030-77424-0_38} }- Ngoc Quy Tran
Hong Quang Nguyen
Van-Phuc Hoang
Year: 2021
Combined VMD-GSO Based Points of Interest Selection Method for Profiled Side Channel Attacks
INISCOM
Springer
DOI: 10.1007/978-3-030-77424-0_38
Abstract
Nowadays, one of the most powerful side channel attacks (SCA) is profiled attack. Machine learning algorithms, for example support vector machine, are currently used for improving the effectiveness of the attack. One issue when using SVM-based profiled attack is extracting points of interest, or features from power traces. So far, studies in SCA domain have selected the points of interest (POIs) from the raw power trace for the classifiers. Our work proposes a novel method for finding POIs that based on the combining variational mode decomposition (VMD) and Gram-Schmidt orthogonalization (GSO). That is, VMD is used to decompose the power traces into sub-signals (modes) of different frequencies and POIs selection process based on GSO is conducted on these sub-signals. As a result, the selected POIs are used for SVM classifier to conduct profiled attack. This attack method outperforms other profiled attacks in the same attack scenario. Experiments were performed on a trace data set collected from the Atmega8515 smart card run on the side channel evaluation board Sakura-G/W and the data set of DPA contest v4 to verify the effectiveness of our method in reducing number of power traces for the attacks, especially with noisy power traces.
