Mouse Behavior Analysis Based on Artificial Intelligence as a Second-Phase Authentication System
- Daniel Garabato 1
- Jorge Rodríguez García
- Francisco J. Novoa 1
- Carlos Dafonte 1
-
1
Universidade da Coruña
info
- Alberto Alvarellos González (ed. lit.)
- José Joaquim de Moura Ramos (ed. lit.)
- Beatriz Botana Barreiro (ed. lit.)
- Javier Pereira Loureiro (ed. lit.)
- Manuel F. González Penedo (ed. lit.)
Publisher: MDPI
ISBN: 978-3-03921-444-0, 978-3-03921-443-3
Year of publication: 2019
Congress: XoveTIC (2. 2019. A Coruña)
Type: Conference paper
Abstract
Nowadays, a wide variety of computer systems use authentication protocols based on several factors in order to enhance security. In this work, the viability of a second-phase authentication scheme based on users’ mouse behavior is analyzed by means of classical Artificial Intelligence techniques, such as the Support Vector Machines or Multi-Layer Perceptrons. Such methods were found to perform particularly well, demonstrating the feasibility of mouse behavior analytics as a second-phase authentication mechanism. In addition, in the current stage of the experiments, the classification techniques were found to be very stable for the extracted features.