Event-based Liveness Detection using Temporal Ocular Dynamics: An Exploratory Approach

TL;DR

This paper investigates using event cameras to improve face liveness detection by analyzing rapid eye movements, achieving high accuracy and demonstrating the potential of event-based sensing for robust biometric security.

Contribution

It introduces an event-based approach for liveness detection, extending existing datasets with replay attack recordings and demonstrating effective classification using spiking neural networks.

Findings

Achieved up to 95.37% top-1 accuracy in liveness classification.

Event-based features effectively distinguish genuine from replayed eye movements.

Event cameras capture microsecond-level ocular dynamics, enhancing detection robustness.

Abstract

Face liveness detection has been extensively studied using RGB cameras, achieving strong performance under controlled conditions but often failing to generalize across sensors and attack scenarios. In this work, we explore event cameras as an alternative sensing modality for liveness detection based on temporal ocular dynamics. Event cameras capture sparse, asynchronous changes in brightness with microsecond resolution, enabling precise analysis of fast eye movements such as saccades. Replay attacks cannot faithfully reproduce these dynamics due to temporal resampling and display artifacts, leading to distinctive spatio-temporal patterns in the event domain. We design a data collection protocol to extend RGBE-Gaze with replay-attack recordings, yielding an event-based fake counterpart for liveness detection. We analyze event-driven temporal features from eye regions and evaluate their effectiveness for ocular motion segmentation and liveness classification. Our results show that event-based representations enable reliable discrimination between genuine and replayed sequences, achieving up to 95.37% top-1 accuracy with a spiking convolutional neural network. These preliminary findings highlight the potential of event-based sensing for robust and low-latency liveness detection.