Unified Detection of Digital and Physical Face Attacks
This addresses the need for robust, generalized defense mechanisms against diverse face attacks, which is crucial for security applications, though it is incremental as it builds on multi-task learning and clustering methods.
The paper tackles the problem of poor generalization in face attack detection across adversarial, digital manipulation, and physical spoof categories by proposing UniFAD, a unified framework that clusters 25 coherent attack types, achieving an overall TDR of 94.73% at 0.2% FDR on a large dataset.
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.