Using mouse dynamics for continuous user authentication

Abstract

This paper suggests a new model for user authentication based on mouse dynamics. The proposed model utilizes a neural network to identify user behavior and Gaussian Naïve Bayes classifier is applied for classification purpose and assessing the ability of the proposed model to distinguish between genuine and imposter user. The performance of the proposed model is examined on a dataset of 48 users. The results prove that the proposed model outperforms other models in all evaluation metrics including, accuracy, false accept rate, false reject rate and error equal rate.