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

arXiv cs.CV / 4/30/2026

📰 NewsModels & Research

共有:

Key Points

The paper addresses a key limitation of RGB-based face liveness detection—reduced generalization across sensors and attack types—by exploring event cameras for liveness recognition.
It argues that replay attacks struggle to reproduce event-camera “temporal ocular dynamics” because temporal resampling and display artifacts distort the spatio-temporal event patterns.
The authors extend an existing RGBE-Gaze dataset by adding replay-attack recordings, creating an event-based “fake” counterpart for training and evaluation.
Using event-driven temporal features from eye regions, they demonstrate ocular motion segmentation and liveness classification with a spiking convolutional neural network, reaching up to 95.37% top-1 accuracy.
The exploratory results suggest event-based sensing could improve robustness and enable low-latency liveness detection by leveraging microsecond-resolution eye dynamics.

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.