Effective Feature Extraction Method for SVM-Based Profiled Attacks

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.