A study on the stability of EEG signals for user authentication

Abstract

Electroencephalography (EEG) has been recently used as a new type of biometrics in user authentication with the advantages of being difficult to fake, impossible to observe or intercept, unique, and requiring alive person to record. However, understanding of the stability of brain responses to EEG-based authentication system while EEG is known to be sensitive to emotions is still a challenge that is addressed in this paper. Our experimental results and the related neurophysiological evidences show that some emotions should be considered to mitigate the impact of EEG signal changes on the EEG-based user authentication system in real-world applications.