MADation: Face Morphing Attack Detection with Foundation Models

TL;DR

MADation leverages foundation models with adaptation techniques to effectively detect face morphing attacks, outperforming existing methods and advancing the state-of-the-art in MAD.

Contribution

This work is the first to adapt foundation models specifically for face morphing attack detection, demonstrating improved performance over previous approaches.

Findings

MADation surpasses alternative FM and transformer-based frameworks.

It achieves competitive results with current MAD solutions.

The implementation is publicly available for reproducibility.

Abstract

Despite the considerable performance improvements of face recognition algorithms in recent years, the same scientific advances responsible for this progress can also be used to create efficient ways to attack them, posing a threat to their secure deployment. Morphing attack detection (MAD) systems aim to detect a specific type of threat, morphing attacks, at an early stage, preventing them from being considered for verification in critical processes. Foundation models (FM) learn from extensive amounts of unlabelled data, achieving remarkable zero-shot generalization to unseen domains. Although this generalization capacity might be weak when dealing with domain-specific downstream tasks such as MAD, FMs can easily adapt to these settings while retaining the built-in knowledge acquired during pre-training. In this work, we recognize the potential of FMs to perform well in the MAD task when properly adapted to its specificities. To this end, we adapt FM CLIP architectures with LoRA weights while simultaneously training a classification header. The proposed framework, MADation surpasses our alternative FM and transformer-based frameworks and constitutes the first adaption of FMs to the MAD task. MADation presents competitive results with current MAD solutions in the literature and even surpasses them in several evaluation scenarios. To encourage reproducibility and facilitate further research in MAD, we publicly release the implementation of MADation at https://github.com/gurayozgur/MADation