PulseAugur
LIVE 09:02:52
research · [2 sources] ·
0
research

Event cameras detect liveness with 95% accuracy using eye dynamics

Researchers have explored using event cameras for face liveness detection, focusing on temporal ocular dynamics. Unlike traditional RGB cameras, event cameras capture asynchronous brightness changes with high temporal resolution, allowing for precise analysis of eye movements like saccades. These cameras can distinguish between genuine and replayed sequences because replay attacks struggle to replicate the natural dynamics, leading to detectable spatio-temporal patterns. The study achieved up to 95.37% accuracy using a spiking convolutional neural network, indicating potential for robust and low-latency liveness detection. AI

Summary written by gemini-2.5-flash-lite from 2 sources. How we write summaries →

IMPACT Event cameras offer a novel approach to liveness detection, potentially improving security against spoofing attacks.

RANK_REASON This is a research paper published on arXiv detailing a new approach to face liveness detection.

Read on arXiv cs.CV →

COVERAGE [2]

  1. arXiv cs.CV TIER_1 · Nicolas Mastropasqua, Ignacio Bugueno-Cordova, Rodrigo Verschae, Daniel Acevedo, Pablo Negri ·

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

    arXiv:2604.26285v1 Announce Type: new 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 cam…

  2. arXiv cs.CV TIER_1 · Pablo Negri ·

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

    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 live…