VoxAtnNet: A 3D Point Clouds Convolutional Neural Network for Generalizable Face Presentation Attack Detection

TL;DR

VoxAtnNet is a novel 3D point cloud convolutional neural network designed for face presentation attack detection, leveraging spatial voxelization and attention mechanisms to improve detection of sophisticated 3D face masks on smartphones.

Contribution

This work introduces VoxAtnNet, a new PAD algorithm utilizing 3D point clouds and convolutional attention networks, with a comprehensive dataset and evaluation protocols for face attack detection.

Findings

Outperforms existing methods in detecting known and unknown PAs

Effective on a new dataset with 3480 samples including 3D silicone masks

Demonstrates robustness against sophisticated 3D presentation attacks

Abstract

Facial biometrics are an essential components of smartphones to ensure reliable and trustworthy authentication. However, face biometric systems are vulnerable to Presentation Attacks (PAs), and the availability of more sophisticated presentation attack instruments such as 3D silicone face masks will allow attackers to deceive face recognition systems easily. In this work, we propose a novel Presentation Attack Detection (PAD) algorithm based on 3D point clouds captured using the frontal camera of a smartphone to detect presentation attacks. The proposed PAD algorithm, VoxAtnNet, processes 3D point clouds to obtain voxelization to preserve the spatial structure. Then, the voxelized 3D samples were trained using the novel convolutional attention network to detect PAs on the smartphone. Extensive experiments were carried out on the newly constructed 3D face point cloud dataset comprising bona fide and two different 3D PAIs (3D silicone face mask and wrap photo mask), resulting in 3480 samples. The performance of the proposed method was compared with existing methods to benchmark the detection performance using three different evaluation protocols. The experimental results demonstrate the improved performance of the proposed method in detecting both known and unknown face presentation attacks.