Face Morphing Attack Detection with Denoising Diffusion Probabilistic Models

TL;DR

This paper introduces a diffusion-based face morphing attack detection method that learns solely from genuine images, effectively identifying various morphing attacks as out-of-distribution samples and demonstrating strong performance across multiple datasets.

Contribution

The paper presents a novel diffusion-based MAD approach that improves generalization by training only on bona fide images, unlike traditional discriminative models.

Findings

Achieves high detection accuracy across four datasets.

Outperforms existing discriminative MAD methods.

Effectively detects unknown morphing attack types.

Abstract

Morphed face images have recently become a growing concern for existing face verification systems, as they are relatively easy to generate and can be used to impersonate someone's identity for various malicious purposes. Efficient Morphing Attack Detection (MAD) that generalizes well across different morphing techniques is, therefore, of paramount importance. Existing MAD techniques predominantly rely on discriminative models that learn from examples of bona fide and morphed images and, as a result, often exhibit sub-optimal generalization performance when confronted with unknown types of morphing attacks. To address this problem, we propose a novel, diffusion-based MAD method in this paper that learns only from the characteristics of bona fide images. Various forms of morphing attacks are then detected by our model as out-of-distribution samples. We perform rigorous experiments over four different datasets (CASIA-WebFace, FRLL-Morphs, FERET-Morphs and FRGC-Morphs) and compare the proposed solution to both discriminatively-trained and once-class MAD models. The experimental results show that our MAD model achieves highly competitive results on all considered datasets.