20.500.12556/RUL-175992 SelfMAD++ self-supervised foundation model with local feature enhancement for generalized morphing attack detection Face morphing attacks pose a growing threat to biometric systems, exacerbated by the rapid emergence of powerful generative techniques that enable realistic and seamless facial image manipulations. To address this challenge, we introduce SelfMAD++, a robust and generalized single-image morphing attack detection (S-MAD) framework. Unlike our previous work SelfMAD, which introduced a data augmentation technique to train off-the-shelf classifiers for attack detection, SelfMAD++ advances this paradigm by integrating the artifact-driven augmentation with foundation models and fine-grained spatial reasoning. At its core, SelfMAD++ builds on CLIP–a vision-language foundation model–adapted via Low-Rank Adaptation (LoRA) to align image representations with task-specific text prompts. To enhance sensitivity to spatially subtle and fine-grained artifacts, we integrate a parallel multi-scale convolutional branch specialized in dense, multi-scale feature extraction. This branch is guided by an auxiliary segmentation module, which acts as a regularizer by disentangling bona fide facial regions from potentially manipulated ones. The dual-branch features are adaptively fused through a gated attention mechanism, capturing both semantic context and fine-grained spatial cues indicative of morphing. SelfMAD++ is trained end-to-end using a multi-objective loss that balances semantic alignment, segmentation consistency, and classification accuracy. Extensive experiments across nine standard benchmark datasets demonstrate that SelfMAD++ achieves state-of-the-art performance, with an average Equal Error Rate (EER) of 3.91 %, outperforming both supervised and unsupervised MAD methods by large margins. Notably, SelfMAD++ excels on modern, high-quality morphs generated by GAN and diffusion–based morphing methods, demonstrating its robustness and strong generalization capability. SelfMAD++ code and supplementary resources are publicly available at: https://github.com/LeonTodorov/SelfMADpp. morphing attack detection MAD face biometrics deep learning foundation models self-supervised learning localized visual reasoning zaznavanje napadov z zlivanjem obrazov obrazna biometrija globoko učenje temeljni modeli samonadzorovano učenje lokalizirano vizualno sklepanje true false true Angleški jezik Slovenski jezik Članek v reviji 2025-11-17 13:28:54 2025-11-17 13:29:02 2026-07-07 04:17:35 0000-00-00 00:00:00 2026 0 0 16 str. pt. C, art. 103921 Vol. 127 Mar. 2026 0000-00-00 Zaloznikova Objavljeno apc 0000-00-00 0000-00-00 0000-00-00 004.93 1872-6305 10.1016/j.inffus.2025.103921 257476867 1-s2.0-S1566253525009832-main.pdf 1-s2.0-S1566253525009832-main.pdf 1 60D170B366A83A54358C7C42CC88FF32 5ca89ecadecece81de59b6a97632f82c4e506db0b1494f80e637602b459e4031 1af9f845-7921-11f1-9b0d-0050569b8976 https://repozitorij.uni-lj.si/Dokument.php?lang=slv&id=237098 https://www.sciencedirect.com/science/article/pii/S1566253525009832 1 a92f6a62-c3b0-11f0-9328-0050569b8976 https://repozitorij.uni-lj.si/Dokument.php?lang=slv&id=222001 Fakulteta za elektrotehniko Fakulteta za računalništvo in informatiko 0 0 0