The security of cryptographic systems is a major conce for cryptosystem designers, even though cryptography algorithms have been improved. Side-channel attacks, by taking advantage of physical vulnerabilities of cryptosystems, aim to gain secret information. Several approaches have been proposed to analyze side-channel information, among which machine leaing is known as a promising method. Machine leaing in terms of neural networks leas the signature (power consumption and electromagnetic emission) of an instruction, and then recognizes it automatically. In this paper, a novel experimental investigation was conducted on field-programmable gate array (FPGA) implementation of elliptic curve cryptography (ECC), to explore the efficiency of side-channel information characterization based on a leaing vector quantization (LVQ) neural network. The main characteristics of LVQ as a multi-class classifi er are that it has the ability to lea complex non-linear input-output relationships, use sequential training procedures, and adapt to the data. Experimental results show the performance of multi-class classifi cation based on LVQ as a powerful and promising approach of side-channel data characterization.