Generalized Single-Image-Based Morphing Attack Detection Using Deep Representations from Vision Transformer

TL;DR

This paper introduces a novel single-image morphing attack detection method using Vision Transformer representations, demonstrating improved generalization and detection performance over existing CNN-based approaches in face recognition security.

Contribution

The paper presents a generalized single-image MAD algorithm based on ViT, which effectively captures local and global face features for robust morphing attack detection.

Findings

Improved detection performance on inter-dataset tests.

Comparable performance on intra-dataset tests.

Outperforms state-of-the-art CNN-based MAD methods.

Abstract

Face morphing attacks have posed severe threats to Face Recognition Systems (FRS), which are operated in border control and passport issuance use cases. Correspondingly, morphing attack detection algorithms (MAD) are needed to defend against such attacks. MAD approaches must be robust enough to handle unknown attacks in an open-set scenario where attacks can originate from various morphing generation algorithms, post-processing and the diversity of printers/scanners. The problem of generalization is further pronounced when the detection has to be made on a single suspected image. In this paper, we propose a generalized single-image-based MAD (S-MAD) algorithm by learning the encoding from Vision Transformer (ViT) architecture. Compared to CNN-based architectures, ViT model has the advantage on integrating local and global information and hence can be suitable to detect the morphing traces widely distributed among the face region. Extensive experiments are carried out on face morphing datasets generated using publicly available FRGC face datasets. Several state-of-the-art (SOTA) MAD algorithms, including representative ones that have been publicly evaluated, have been selected and benchmarked with our ViT-based approach. Obtained results demonstrate the improved detection performance of the proposed S-MAD method on inter-dataset testing (when different data is used for training and testing) and comparable performance on intra-dataset testing (when the same data is used for training and testing) experimental protocol.