Multi-class SVMs analysis of side-channel information of elliptic curve cryptosystem

Cryptosystems, even after recent algorithmic improvements, can be vulnerable to side-channel attacks (SCA). In this paper, we investigate one of the powerful class of SCAs based on machine learning techniques in the forms of Principal Component Analysis (PCA) and multi-class classification. For this purpose, a support vector machine (SVM) is investigated as a robust and efficient multi-class classifier along with a proper kernel function and its appropriate parameters. Our experiment performed on data leakage of a FPGA implementation of elliptic curve cryptography (ECC), and the results, validated by cross-validation approach, compare the efficiency of different kernel functions and the influence of function parameters.