Evaluating the Effectiveness of Attack-Agnostic Features for Morphing Attack Detection

Morphing attacks have diversified significantly over the past years, with new methods based on generative adversarial networks (GANs) and diffusion models posing substantial threats to face recognition systems. Recent research has demonstrated the effectiveness of features extracted from large vision models pretrained on bonafide data only (attack-agnostic features) for detecting deep generative images. Building on this, we investigate the potential of these image representations for morphing attack detection (MAD). We develop supervised detectors by training a simple binary linear SVM on the extracted features and one-class detectors by modeling the distribution of bonafide features with a Gaussian Mixture Model (GMM). Our method is evaluated across a comprehensive set of attacks and various scenarios, including generalization to unseen attacks, different source datasets, and print-scan data. Our results indicate that attack-agnostic features can effectively detect morphing attacks, outperforming traditional supervised and one-class detectors from the literature in most scenarios. Additionally, we provide insights into the strengths and limitations of each considered representation and discuss potential future research directions to further enhance the robustness and generalizability of our approach.

1. Introduction

Morphing attacks pose a significant threat to face recognition (FR) systems. These attacks involve creating a composite passport image that merges facial features from two distinct source identities. This manipulated image is then submitted to governmental services for passport applications, a process still allowed in several European countries where applicants can provide their own photographs. In successful morphing attacks, both contributing individuals can then authenticate against the altered image, enabling them to share a single passport. This undermines the security and effectiveness of automated border control (ABC) systems.