DifFoundMAD: Foundation Models meet Differential Morphing Attack Detection

TL;DR

DifFoundMAD is a parameter-efficient framework leveraging vision foundation models to improve differential morphing attack detection, significantly reducing error rates in security-critical scenarios.

Contribution

It introduces a novel FM-based D-MAD approach with lightweight fine-tuning, outperforming existing methods across multiple benchmarks.

Findings

Achieves a reduction in error rates from 6.16% to 2.17% at high-security levels.

Demonstrates consistent improvements over state-of-the-art D-MAD systems.

Effective cross-database generalization of the proposed method.

Abstract

In this work, we introduce DifFoundMAD, a parameter-efficient D-MAD framework that exploits the generalisation capabilities of vision foundation models (FM) to capture discrepancies between suspected morphs and live capture images. In contrast to conventional D-MAD systems that rely on face recognition embeddings or handcrafted feature differences, DifFoundMAD follows the standard differential paradigm while replacing the underlying representation space with embeddings extracted from FMs. By combining lightweight finetuning with class-balanced optimisation, the proposed method updates only a small subset of parameters while preserving the rich representational priors of the underlying FMs. Extensive cross-database evaluations on standard D-MAD benchmarks demonstrate that DifFoundMAD achieves consistent improvements over state-of-the-art systems, particularly at the strict security levels required in operational deployments such as border control: The error rates reported in the current state-of-the-art were reduced from 6.16% to 2.17% for high-security levels using DifFoundMAD.