An Encephalogram (EEG) Based Biometrics Investigation for Authentication: A HumanComputer Interaction (HCI) Approach Ricardo J. Rodriguez – Advisor: Dr. Maxine Cohen Problem Statement Traditional authentication methods rely on “what you know” (i.e., knowledge-based authenticator) or “what you have” (i.e., objectbased authenticator) to identify users. These are susceptible to inadvertent disclosure or can be simply lost or stolen (O’Gorman, 2003).“What you are” (i.e., ID-based authenticator) clearly provides an edge since individuals are “who they are” regardless of “what they know” or “what they have”. Additionally, EEG devices are undergoing a significant evolution that is leading to their acceptance as Brain-Computer Interfaces (BCI) by an increasing number of users (Minnery and Fine, 2009). This creates an opportunity to exploit the unique “inner-self” of a person for authentication purposes. EEG Based Biometrics System Processing Visual Stimuli Auditory Stimuli Tactile Stimuli Action Olfactory Stimuli Gustatory Stimuli Solution Approach • Leverage emotionally meaningful visual stimuli • Record resulting Visual Evoked Potentials (VEPs) as EEG signals • Process and extract features from EEG Signals • Develop AI Model (e.g., Support Vector Machine) • Analyze results to determine accuracy • Measure User Acceptance Key Resources • • • • Research Goal Research Questions The goal of this work is to develop and evaluate the effectiveness of an EEG-based biometric authentication mechanism to addresses some of the common shortfalls of current systems. The proposed approach leverages the unique “inner-self” of a person, which is expected to be different between people performing similar tasks (Zúquete, Quintela, and Cunha, 2011). RQ1. What level of accuracy will the proposed EEG-based biometric access control mechanism provide? – Key Metrics: False Acceptance Rate (FAR), False Rejection Rate (FRR), and Equal Error Rate (EER). RQ2. How will the proposed EEG-based biometric access control mechanism be perceived by users (i.e., acceptability and user satisfaction)? Emotiv EEG Headset Emotiv Research SDK Matlab HCILab and BCILab Key References Minnery, B. S., & Fine, M. S. (2009). Feature: Neuroscience and the future of human-computer interaction. Interactions, 16 (2), 70-75. doi:10.1145/1487632.1487649 O'Gorman, L. (2003). Comparing passwords, tokens, and biometrics for user authentication. Proceedings of the IEEE, 91(12), 2021-2040. doi:10.1109/jproc.2003.819611 Zúquete, A., Quintela, B., & Cunha, J. (2011). Biometric Authentication with Electroencephalograms: Evaluation of Its Suitability Using Visual Evoked Potentials. In A. Fred, J. Filipe & H. Gamboa (Eds.), Biomedical Engineering Systems and Technologies (Vol. 127, pp. 290-306): Springer Berlin Heidelberg.
© Copyright 2020 ExploreDoc