MusicID: A Brainwave-based User Authentication System for Internet of Things

TL;DR

MusicID is a brainwave-based authentication system for IoT devices that achieves high accuracy using commodity EEG headsets listening to music, enabling continuous and user-friendly security for smart devices.

Contribution

This paper introduces MusicID, a novel authentication method leveraging music-induced brainwave patterns with high accuracy using low-cost EEG devices.

Findings

Over 98% accuracy for user identification.

Single electrode achieves ~85% accuracy.

Two electrodes achieve ~95% accuracy.

Abstract

We propose MusicID, an authentication solution for smart devices that uses music-induced brainwave patterns as a behavioral biometric modality. We experimentally evaluate MusicID using data collected from real users whilst they are listening to two forms of music; a popular English song and individual's favorite song. We show that an accuracy over 98% for user identification and an accuracy over 97% for user verification can be achieved by using data collected from a 4-electrode commodity brainwave headset. We further show that a single electrode is able to provide an accuracy of approximately 85% and the use of two electrodes provides an accuracy of approximately 95%. As already shown by commodity brain-sensing headsets for meditation applications, we believe including dry EEG electrodes in smart-headsets is feasible and MusicID has the potential of providing an entry point and continuous authentication framework for upcoming surge of smart-devices mainly driven by Augmented Reality (AR)/Virtual Reality (VR) applications.