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

2026-04-29

AI Summary

This work addresses the limited generalization of conventional RGB-based face liveness detection under cross-sensor conditions and replay attacks. It pioneers the integration of event cameras into eye-movement-based liveness detection, leveraging their microsecond-level temporal resolution to capture distinctive spatiotemporal signatures of genuine blinks and eye movements in the event domain, thereby effectively discriminating real faces from replayed ones. The proposed approach combines event-stream feature extraction from the periocular region with a Spiking Convolutional Neural Network (Spiking CNN). Evaluated on a newly collected replay-attack dataset, the method achieves a Top-1 accuracy of 95.37%, demonstrating the potential of event-based sensing for low-latency, highly robust liveness detection.

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.

Problem

• face liveness detection
• replay attacks
• event cameras
• temporal ocular dynamics
• generalization

Innovation

• event camera
• temporal ocular dynamics
• liveness detection
• replay attack
• spiking convolutional neural network