Seeing Is Believing: Authenticating Users with What They See and Remember

Abstract

Brainwaves, as external signals of a functioning brain, provide a possible glimpse into how we think and react. However, seen another way, we could reasonably expect that a given action or event could be linked back to its corresponding brainwave reaction. Recently, commercial products in the form of commercial brainwave headsets have flooded into the market, opening up the possibility of exploiting brainwaves for various purposes and making this more feasible. In this paper, we build an authentication system based on brainwave reactions to a chain of events. We use a commercially available brainwave headset to collect brainwave data of participants for use in the proposed authentication system. After the brainwave data collection process, we apply a machine learning-based approach to extract features from brainwaves to serve as authentication tokens in the system and to support the authentication system itself.

The work was supported in part by the Academia Sinica, in part by the Taiwan Information Security Center, and in part by the Ministry of Science and Technology, Taiwan under Grants MOST 105-2221-E-259-014-MY3, MOST 105-2221-E-011-070-MY3, MOST 105-2923-E-182-001-MY3, and MOST 106-3114-E-011-003.