XSA-MAD: Cross-modal Semantic Alignment for Morphing Attack Detection

2026-08-13

AI Summary

This study addresses the limited generalizability of existing image manipulation detection methods by proposing a CLIP-based multimodal framework. The approach innovatively decouples manipulation into four interpretable attributes—identity, geometry, texture, and consistency—and constructs a unified semantic representation through progressive cross-modal alignment, enabling generation-agnostic, concept-level discrepancy modeling. By effectively capturing generation-invariant features, the method demonstrates strong generalization on the MAD22 and MorDIFF datasets, achieving an Equal Error Rate (EER) as low as 2.92% for GAN manipulations. Furthermore, it consistently outperforms state-of-the-art approaches in high-fidelity attack scenarios, significantly enhancing detection robustness against diverse and evolving synthetic media threats.

Abstract

Morphing attacks pose a serious threat to face recognition systems. However, existing image-based morphing attack detection (MAD) methods often generalize poorly to unseen generation techniques because they rely solely on visual cues. We propose XSA-MAD, a CLIP-based multimodal framework that explicitly models semantic inconsistencies between bona-fide and morphed faces. Morphing concepts are decomposed into four interpretable attributes, including identity, facial geometry, texture, and consistency, and are encoded as structured and attribute-aware textual representations. The image encoder is progressively aligned with this discriminative textual space, resulting in a unified semantic representation that captures generation-invariant and concept-level discrepancies between bona-fide and morph images. Experiments on MAD22 and MorDIFF, following training on SMDD, demonstrate strong generalization across diverse morphing principles. In particular, XSA-MAD achieves an equal error rate of 2.92% on GAN-based morphs and consistently outperforms existing methods under high-fidelity generative attacks.

Problem

• Morphing Attack Detection
• Generalization
• Face Recognition
• Cross-modal Semantic Alignment

Innovation

• Cross-modal Semantic Alignment
• CLIP-based Multimodal Framework
• Morphing Attack Detection
• Attribute-aware Textual Representation
• Generalization