Unified Detection of Digital and Physical Face Attacks

TL;DR

This paper introduces UniFAD, a unified face attack detection framework that effectively clusters and detects 25 attack types across digital, physical, and adversarial categories, outperforming existing methods.

Contribution

UniFAD is a novel multi-task learning approach that automatically clusters attack types, improving generalization across attack categories and achieving high detection accuracy.

Findings

Achieves 94.73% TDR at 0.2% FDR on large dataset

Detects attacks within 3 milliseconds

Identifies attack types and categories with high accuracy

Abstract

State-of-the-art defense mechanisms against face attacks achieve near perfect accuracies within one of three attack categories, namely adversarial, digital manipulation, or physical spoofs, however, they fail to generalize well when tested across all three categories. Poor generalization can be attributed to learning incoherent attacks jointly. To overcome this shortcoming, we propose a unified attack detection framework, namely UniFAD, that can automatically cluster 25 coherent attack types belonging to the three categories. Using a multi-task learning framework along with k-means clustering, UniFAD learns joint representations for coherent attacks, while uncorrelated attack types are learned separately. Proposed UniFAD outperforms prevailing defense methods and their fusion with an overall TDR = 94.73% @ 0.2% FDR on a large fake face dataset consisting of 341K bona fide images and 448K attack images of 25 types across all 3 categories. Proposed method can detect an attack within 3 milliseconds on a Nvidia 2080Ti. UniFAD can also identify the attack types and categories with 75.81% and 97.37% accuracies, respectively.