2020/06/02 by Jinani Sooriyaarachchi, Sooriyaarachchi, Jinani, Suranga Seneviratne +5
Computer Science · Neuroscience · #Cryptography and Security (cs.CR) #EEG and Brain-Computer Interfaces #FOS: Computer and information sciences #FOS: Electrical engineering #Neural dynamics and brain function #Signal Processing (eess.SP) #User Authentication and Security Systems #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2006.01751
openalex publication_date 2020/06/02 · openalex created_date 2022/07/26 · openalex updated_date 2026/07/28
We propose MusicID, an authentication solution for smart devices that uses\nmusic-induced brainwave patterns as a behavioral biometric modality. We\nexperimentally evaluate MusicID using data collected from real users whilst\nthey are listening to two forms of music; a popular English song and\nindividual's favorite song. We show that an accuracy over 98% for user\nidentification and an accuracy over 97% for user verification can be achieved\nby using data collected from a 4-electrode commodity brainwave headset. We\nfurther show that a single electrode is able to provide an accuracy of\napproximately 85% and the use of two electrodes provides an accuracy of\napproximately 95%. As already shown by commodity brain-sensing headsets for\nmeditation applications, we believe including dry EEG electrodes in\nsmart-headsets is feasible and MusicID has the potential of providing an entry\npoint and continuous authentication framework for upcoming surge of\nsmart-devices mainly driven by Augmented Reality (AR)/Virtual Reality (VR)\napplications.\n