Aurora Guard: Real-Time Face Anti-Spoofing via Light Reflection

TL;DR

This paper introduces Aurora Guard, a real-time face anti-spoofing system using light reflection analysis and CNNs, which is effective, fast, and deployed at scale, with a large dataset for training and evaluation.

Contribution

The paper presents a novel light reflection based anti-spoofing method with an end-to-end trainable CNN and a large-scale dataset, advancing real-world face security systems.

Findings

Outperforms existing anti-spoofing methods on public datasets.

Successfully deployed in real-world systems serving millions.

Achieves high accuracy in distinguishing live faces from spoofing attempts.

Abstract

In this paper, we propose a light reflection based face anti-spoofing method named Aurora Guard (AG), which is fast, simple yet effective that has already been deployed in real-world systems serving for millions of users. Specifically, our method first extracts the normal cues via light reflection analysis, and then uses an end-to-end trainable multi-task Convolutional Neural Network (CNN) to not only recover subjects' depth maps to assist liveness classification, but also provide the light CAPTCHA checking mechanism in the regression branch to further improve the system reliability. Moreover, we further collect a large-scale dataset containing $12,000$ live and spoofing samples, which covers abundant imaging qualities and Presentation Attack Instruments (PAI). Extensive experiments on both public and our datasets demonstrate the superiority of our proposed method over the state of the arts.