A Personalised User Authentication System based on EEG Signals

Conventional biometrics have been employed in high security user authentication systems for over 20 years now. However, some of these modalities face low security issues in common practice. Brain wave based user authentication has emerged as a promising alternative method, as it overcomes some of th...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Stergiadis, Christos, Vasiliki-Despoina Kostaridou, Veloudis, Simeon, Kazis, Dimitrios, Klados, Manousos
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 14.07.2022
Subjects
Algorithms
Biometrics
Electroencephalography
Feature extraction
Machine learning
Security
Online AccessGet full text

Cover

More Information
Summary:Conventional biometrics have been employed in high security user authentication systems for over 20 years now. However, some of these modalities face low security issues in common practice. Brain wave based user authentication has emerged as a promising alternative method, as it overcomes some of these drawbacks and allows for continuous user authentication. In the present study we address the problem of individual user variability, by proposing a data-driven Electroencephalography (EEG) based authentication method. We introduce machine learning techniques, in order to reveal the optimal classification algorithm that best fits the data of each individual user, in a fast and efficient manner. A set of 15 power spectral features (delta, theta, lower alpha, higher alpha, and alpha) is extracted from the three EEG channels. The results show that our approach can reliably grant or deny access to the user (mean accuracy 95,6%), while at the same time poses as a viable option for real time applications, as the total time of the training procedure was kept under one minute.
ISSN:2331-8422