Conference
Open access
Aug 2026
XSA-Mad: Cross-Modal Semantic Alignment for Morphing Attack Detection
XSA-MAD, a CLIP-based multimodal framework that explicitly models semantic inconsistencies between bona-fide and morphed faces, is proposed, a CLIP-based multimodal framework that consistently outperforms existing methods under high-fidelity generative attacks.
Jie Jin, Mahiro Tokumasu, Yushi Makino et al.
· International Conference on... · 0 citations