2026 |
Chettaoui, Tahar; Ozgur, Guray; Caldeira, Eduarda; Nakvosas, Arturas; Shahreza, Hatef Otroshi; Marcel, Sebastien; Shukla, Rishabh; Takkar, Aditya; Khullar, Rushil; Yadav, Lalak; Gupta, Gourav; Gupta, Anant; Yu, Shiqi; Štruc, Vitomir; Damer, Naser; Boutros, Fadi IJCB-AFMFR 2026: Competition on Adapting Foundation Models for Face Recognition Using Synthetic Training Data Proceedings Article In: Proceedings of the IEEE/IAPR International Joint Conference on Biometrics (IJCB), pp. 1–12, 2026. Links | BibTeX | Tags: biometrics, competition IJCB, face recognition, foundation models @inproceedings{IJCBFaceCom2026, |
Ivanovska, Marija; Todorov, Leon; Peer, Peter; Štruc, Vitomir SelfMAD++: Self-Supervised Foundation Model with Local Feature Enhancement for Generalized Morphing Attack Detection Journal Article In: Information Fusion, vol. 127, Part C, no. 103921, pp. 1-16, 2026. Abstract | Links | BibTeX | Tags: anomaly detection, biometrics, CLIP, computer vision, face morphing detection, face recognition, foundation models @article{InfoFUS_Marija,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. |
2025 |
Caldeira, Eduarda; Ozgur, Guray; Chettaoui, Tahar; Ivanovska, Marija; Peer, Peter; Boutros, Fadi; Struc, Vitomir; Damer, Naser MADation: Face Morphing Attack Detection with Foundation Models Proceedings Article In: Proceedings of IEEE/CFV Winter Conference on Applications in Computer Vision - Workshops (WACV-W) 2025, pp. 1-11, Tucson, USA, 2025. Abstract | Links | BibTeX | Tags: face morphing, face morphing attack, face morphing detection, foundation models, morphing attack, morphing attack detection @inproceedings{FadiWACV2025_Foundation,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. |