Visible to the public Brain-Computer Interface based User Authentication System for Personal Device Security

TitleBrain-Computer Interface based User Authentication System for Personal Device Security
Publication TypeConference Paper
Year of Publication2020
AuthorsHossain, T., rakshit, A., Konar, A.
Conference Name2020 International Conference on Computer, Electrical Communication Engineering (ICCECE)
Date PublishedJan. 2020
ISBN Number978-1-7281-4476-4
Keywords3 × 3 spatial matrix, BCI, biometric security, BIOS, brain, brain pattern classification, brain-computer interface system, brain-computer interfaces, CCA, EKF, electroencephalography, EMD, ERNN, extended-Kalman filter, flickering circle, Human Behavior, Kalman filters, mentally selected circle, mentally uttered number, Metrics, particle filter, password, personal device security, PF, pubcrawl, recurrent neural nets, recurrent neural network, resilience, Resiliency, RNN, Scalability, security, security of data, SSVEP brain pattern, two stage security verification, user authentication system, visual evoked potentials

The paper proposes a novel technique of EEG induced Brain-Computer Interface system for user authentication of personal devices. The scheme enables a human user to lock and unlock any personal device using his/her mind generated password. A two stage security verification is employed in the scheme. In the first stage, a 3 x 3 spatial matrix of flickering circles will appear on the screen of which, rows are blinked randomly and user has to mentally select a row which contains his desired circle.P300 is released when the desired row is blinked. Successful selection of row is followed by the selection of a flickering circle in the desired row. Gazing at a particular flickering circle generates SSVEP brain pattern which is decoded to trace the mentally selected circle. User is able to store mentally uttered number in the selected circle, later the number with it's spatial position will serve as the password for the unlocking phase. Here, the user is equipped with a headphone where numbers starting from zero to nine are spelled randomly. Spelled number matching with the mentally uttered number generates auditory P300 in the subject's brain. The particular choice of mentally uttered number is detected by successful detection of auditory P300. A novel weight update algorithm of Recurrent Neural Network (RNN), based on Extended-Kalman Filter and Particle Filter is used here for classifying the brain pattern. The proposed classifier achieves the best classification accuracy of 95.6%, 86.5% and 83.5% for SSVEP, visual P300 and auditory P300 respectively.

Citation Keyhossain_brain-computer_2020