Eye Movement Biometrics in Virtual Reality: A Comparison Between VR Headset and High-End Eye-Tracker Collected Dataset

Previous studies have shown that eye movement data recorded at 1000 Hz can authenticate individuals. This study explores the effectiveness of eye movement-based biometrics by utilizing data from an eye-tracking-enabled virtual reality headset (GazeBaseVR) and compares its performance to that of a high-end eye tracker that has been downsampled to the same sampling rate. The GazeBase Vrdataset achieves an equal error rate (EER) of 1.92% and a false rejection rate (FRR) of 16.65% at a 10–<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">4</sup> false acceptance rate (FAR) in a monocular configuration, with a decidability index of 3.43. This study underscores the biometric viability of data obtained from eye-tracking-enabled VR headsets.