Abstract
This study investigates the effects of occlusions on the fairness of face recognition systems, particularly focusing on demographic biases. Using the Racial Faces in the Wild (RFW) dataset and synthetically added realistic occlusions, we evaluate their effect on the performance of face recognition models trained on the BUPT-Balanced and BUPT-GlobalFace datasets. We note increases in the dispersion of FMR, FNMR, and accuracy alongside decreases in fairness according to Equalized Odds, Demographic Parity, STD of Accuracy, and Fairness Discrepancy Rate. Additionally, we utilize a pixel attribution method to understand the importance of occlusions in model predictions, proposing a new metric, Face Occlusion Impact Ratio (FOIR), that quantifies the extent to which occlusions affect model performance across different demographic groups. Our results indicate that occlusions exacerbate existing demographic biases, with models placing higher importance on occlusions in an unequal fashion across demographics.

Abstract
Leveraging the capabilities of Knowledge Distillation (KD) strategies, we devise a strategy to fight the recent retraction of face recognition datasets. Given a pretrained Teacher model trained on a real dataset, we show that carefully utilising synthetic datasets, or a mix between real and synthetic datasets to distil knowledge from this teacher to smaller students can yield surprising results. In this sense, we trained 33 different models with and without KD, on different datasets, with different architectures and losses. And our findings are consistent, using KD leads to performance gains across all ethnicities and decreased bias. In addition, it helps to mitigate the performance gap between real and synthetic datasets. This approach addresses the limitations of synthetic data training, improving both the accuracy and fairness of face recognition models.

Abstract
Face recognition technology, despite its advancements and increasing accuracy, still presents significant challenges in explainability and ethical concerns, especially when applied in sensitive domains such as surveillance, law enforcement, and access control. The opaque nature of deep learning models jeopardises transparency, bias, and user trust. Concurrently, the proliferation of web applications presents a unique opportunity to develop accessible and interactive tools for demonstrating and analysing these complex systems. These tools can facilitate model decision exploration with various images, aiding in bias mitigation or enhancing users’ trust by allowing them to see the model in action and understand its reasoning. We propose an explainable face recognition web application designed to support enrolment, identification, authentication, and verification while providing visual explanations through pixel-wise importance maps to clarify the model’s decision-making process. The system is built in compliance with the European Union General Data Protection Regulation, ensuring data privacy and user control over personal information. The application is also designed for scalability, capable of efficiently managing large datasets. Load tests conducted on databases containing up to 1,000,000 images confirm its efficiency. This scalability ensures robust performance and a seamless user experience even with database growth. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

Abstract
Face recognition (FR) systems are vulnerable to morphing attacks, which refer to face images created by morphing the facial features of two different identities into one face image to create an image that can match both identities, allowing serious security breaches. In this work, we apply a frequency-based explanation method from the area of explainable face recognition to shine a light on how FR models behave when processing a bona fide or attack pair from a frequency perspective. In extensive experiments, we used two different state-of-the-art FR models and six different morphing attacks to investigate possible differences in behavior. Our results show that FR models rely differently on different frequency bands when making decisions for bona fide pairs and morphing attacks. In the following step, we show that this behavioral difference can be used to detect morphing attacks in an unsupervised setup solely based on the observed frequency-importance differences in a generalizable manner.

Abstract
[No abstract available]

Abstract
The growing demands of the Blue Economy are increasingly supported by sensing platforms, including as Autonomous Surface Vehicles (ASVs) and Autonomous Underwater Vehicles (AUVs). Multimodal Underwater Wireless Networks (MUWNs), which may combine acoustic, radio-frequency, and optical wireless technologies, enhance underwater data transmission capabilities. Although Delay-Tolerant Networks (DTNs) address connectivity intermittency in such environments, not all data streams are delay-tolerant, and transmitting high-bandwidth DTN traffic over narrowband links can lead to significant inefficiencies. This paper presents QoS-MUWCom, a Quality of Service (QoS)-aware communication solution designed to manage both real-time and delay-tolerant traffic across dynamically selected multimodal interfaces. Experimental evaluations conducted in a freshwater tank demonstrate that QoS-MUWCom achieves near-zero packet loss for low-demand traffic even under link saturation, improves throughput for prioritized flows up to three times in mobility scenarios, and adapts to link availability and node mobility. The results confirm that QoS-MUWCom outperforms conventional multimodal strategies, contributing to more robust, resilient and efficient underwater communications.