Joint Physical-Digital Facial Attack Detection Via Simulating Spoofing Clues

TL;DR

This paper introduces a unified model for detecting both physical and digital face spoofing attacks using novel data augmentation techniques that simulate attack clues, enhancing generalization to unseen attack types.

Contribution

The paper presents a flexible approach with two new augmentation methods, SPSC and SDSC, enabling a single model to effectively detect diverse face spoofing attacks.

Findings

Achieved state-of-the-art generalization on UniAttackData dataset

Won first place in CVPR 2024 Face Anti-spoofing Challenge

Final model achieved low APCER, BPCER, and ACER rates

Abstract

Face recognition systems are frequently subjected to a variety of physical and digital attacks of different types. Previous methods have achieved satisfactory performance in scenarios that address physical attacks and digital attacks, respectively. However, few methods are considered to integrate a model that simultaneously addresses both physical and digital attacks, implying the necessity to develop and maintain multiple models. To jointly detect physical and digital attacks within a single model, we propose an innovative approach that can adapt to any network architecture. Our approach mainly contains two types of data augmentation, which we call Simulated Physical Spoofing Clues augmentation (SPSC) and Simulated Digital Spoofing Clues augmentation (SDSC). SPSC and SDSC augment live samples into simulated attack samples by simulating spoofing clues of physical and digital attacks, respectively, which significantly improve the capability of the model to detect "unseen" attack types. Extensive experiments show that SPSC and SDSC can achieve state-of-the-art generalization in Protocols 2.1 and 2.2 of the UniAttackData dataset, respectively. Our method won first place in "Unified Physical-Digital Face Attack Detection" of the 5th Face Anti-spoofing Challenge@CVPR2024. Our final submission obtains 3.75% APCER, 0.93% BPCER, and 2.34% ACER, respectively. Our code is available at https://github.com/Xianhua-He/cvpr2024-face-anti-spoofing-challenge.