Internet of Medical Things (IoMT) devices are inherently vulnerable to cyberattacks, typically due to their limited processing power and memory capacity. Their widespread use in healthcare poses a significant security risk, threatening patient data privacy and the continuity of services. This study examines the effects of data imbalance correction and balancing strategies on the performance of machine and deep learning models using openly available IoMT datasets. In this context, four different balancing methods—RandomUnderSampler, SMOTE, Borderline-SMOTE, and ADASYN—were applied to three open-access IoMT datasets: ECU-IoHT, WUSTL, and CICIoMT2024. Performance analyses were conducted using five machine learning algorithms (AdaBoost, Logistic Regression, Random Forest, XGBoost, and K-Nearest Neighbor (KNN)) and two deep learning algorithms (Convolutional Neural Networks (CNN) and Deep Neural Networks (DNN)). In the highly imbalanced binary setting of the CICIoMT2024 dataset, the combination of RandomUnderSampler and SMOTE under the balanced-training/original-testing scenario produced the strongest improvement in the binary CICIoMT2024 setting, increasing the F1-Score from the unbalanced baseline to 99.87% for Random Forest and 99.86% for XGBoost across repeated runs. However, the benefit of balancing was not universal. In datasets with stronger class separability, such as ECU-IoHT, and in several multi-class settings, the effect of balancing was limited or, in some cases, inferior to the unbalanced baseline. These findings indicate that balancing is most effective under specific conditions, particularly in highly imbalanced binary tasks, and should be validated using class-sensitive metrics rather than overall performance alone

The shift to software-defined electric vehicles (SDEVs) introduces new challenges in software architecture, driven by the integration of electrification-specific software components. Indeed, unlike traditional software-defined vehicles (SDVs), SDEVs require architectures tailored to e.g., electric propulsion, energy management, battery optimization, and electric motor control. In this paper, we present the findings of a structured survey with twelve automotive software experts who provided insights into current practices and trends in the design and management of the software architecture of SDEVs. The findings highlight that SDEVs architectural trends favor zonal and cross-domain designs to handle mixed-criticality components. Moreover, advanced hardware integration and electrificationspecific features further amplify the need for modular software solutions. The experts further indicated key quality attributes essential for designing the software architecture of SDEVs. The three most reported attributes are safety, security, and reliability, particularly in managing high-voltage and battery systems

Radio Frequency Fingerprinting (RFF) would be a promising Physical Layer Security (PLS) solution for the Internet of Things (IoT) that requires robust, low-overhead security techniques. However, practical implementation of RFF may pose challenges, in particular, performance instability and ethical-regulatory conflicts. Based on authors’ previous research, this paper elaborates these challenges in potential deployment of a resilient and compliant RFF system. First, we analytically show how hardware-induced feature drift, primarily driven by device aging and temperature variations, degrades RFF performance. We then critically survey existing temperature variation and aging models, one of which is being studied by one of the authors’ research team. We look into this from a purely hardware-design perspective, and then compensation methods for an RFF perspective. This reveals a significant gap: current techniques are insufficient to maintain the long-term, high-accuracy RFF for real-world IoT security requirements. Finally, we introduce inherent privacy risks by enabling device tracking. This property conflicts with General Data Protection Regulation (GDPR) mandates, raising significant regulatory challenges and privacy risks. Overall, this work highlights the key technical and legal challenges that must be addressed for RFF to evolve into a robust, privacy-compliant and deployable security primitive for IoT and future wireless systems

Federated unlearning (FU) algorithms allow clients in federated settings to exercise their right to be forgotten by removing the influence of their data from a collaboratively trained model. Existing FU methods maintain data privacy by performing unlearning locally on the client-side and sending targeted updates to the server without exposing forgotten data; yet they often rely on server-side cooperation, revealing the client's intent and identity without enforcement guarantees - compromising autonomy and unlearning privacy. In this work, we propose EFU (Enforced Federated Unlearning), a cryptographically enforced FU framework that enables clients to initiate unlearning while concealing its occurrence from the server. Specifically, EFU leverages functional encryption to bind encrypted updates to specific aggregation functions, ensuring the server can neither perform unauthorized computations nor detect or skip unlearning requests. To further mask behavioral and parameter shifts in the aggregated model, we incorporate auxiliary unlearning losses based on adversarial examples and parameter importance regularization. Extensive experiments show that EFU achieves near-random accuracy on forgotten data while maintaining performance comparable to full retraining across datasets and neural architectures - all while concealing unlearning intent from the server. Furthermore, we demonstrate that EFU is agnostic to the underlying unlearning algorithm, enabling secure, function-hiding, and verifiable unlearning for any client-side FU mechanism that issues targeted updates. © 2025

Device heterogeneity poses major challenges in Federated Learning (FL), where resource-constrained clients slow down synchronous schemes that wait for all updates before aggregation. Asynchronous FL addresses this by incorporating updates as they arrive, substantially improving efficiency. While its efficiency gains are well recognized, its privacy costs remain largely unexplored-particularly for high-end devices that contribute updates more frequently, increasing their cumulative privacy exposure. This paper presents the first comprehensive analysis of the efficiency-fairness-privacy trade-off in synchronous vs. asynchronous FL under realistic device heterogeneity. We empirically compare FedAvg and staleness-aware FedAsync using a physical testbed of five edge devices spanning diverse hardware tiers, integrating Local Differential Privacy (LDP) and the Moments Accountant to quantify per-client privacy loss. Using Speech Emotion Recognition (SER) as a privacy-critical benchmark, we show that FedAsync achieves up to 10× faster convergence but exacerbates fairness and privacy disparities: high-end devices contribute 6-10× more updates and incur up to 5× higher privacy loss, while low-end devices suffer amplified accuracy degradation due to infrequent, stale, and noise-perturbed updates. These findings motivate the need for adaptive FL protocols that jointly optimize aggregation and privacy mechanisms based on client capacity and participation dynamics, moving beyond static, one-size-fits-all solutions

Federated learning is a distributed machine learning approach where end users train local models with their own data and combine model updates on a reliable server to create a global model. Despite its advantages, this distributed structure is vulnerable to attacks as end users keep their data and training process private. Current defense mechanisms often fail when facing different attack types or high percentages of malicious participants. This paper proposes a new defense algorithm called Neuron-Centric Federated Learning Defense (NC-FLD), a novel approach that dynamically identifies and analyzes the most significant neurons across model layers rather than examining entire gradient spaces. Unlike existing methods that analyze all parameters equally, NC-FLD creates feature vectors from specifically selected neurons that show the highest training impact, then applies dimensionality reduction to enhance their discriminative features. We conduct experiments with various attack scenarios and different malicious participant rates across multiple datasets (CIFAR-10, F-MNIST, and MNIST). Additionally, we perform simulations on the GTSR dataset as a real-world application. Experimental results demonstrate that NC-FLD successfully defends against diverse attack scenarios in both IID and non-IID dataset distributions, maintaining accuracy above 70% with 40% malicious participation, a 5–15% improvement over the state-of-the-art method, showing enhanced robustness across diverse data distributions while effectively mitigating the impacts of both data and model poisoning attacks.

Cybersecurity represents a critical challenge for data-sharing platforms involving multiple stakeholders, particularly within complex and decentralized systems such as livestock supply chain networks. These systems demand novel approaches, robust security protocols, and advanced data management strategies to address key challenges such as data consistency, transparency, ownership, controlled access or exposure, and privacy-preserving analytics for value-added services. In this paper, we introduced the Framework for Livestock Empowerment and Decentralized Secure Data eXchange (FLEX), as a comprehensive solution grounded on five core design principles: (i) enhanced security and privacy, (ii) human-centric approach, (iii) decentralized and trusted infrastructure, (iv) system resilience, and (v) seamless collaboration across the supply chain. FLEX integrates interdisciplinary innovations, leveraging decentralized infrastructure-based protocols to ensure trust, traceability, and integrity. It employs secure data-sharing protocols and cryptographic techniques to enable controlled information exchange with authorized entities. Additionally, the use of data anonymization techniques ensures privacy. FLEX is designed and implemented using a microservices architecture and edge computing to support modularity and scalable deployment. These components collectively serve as a foundational pillar of the development of a digital product passport. The FLEX architecture adopts a layered design and incorporates robust security controls to mitigate threats identified using the STRIDE threat modeling framework. The evaluation results demonstrate the framework’s effectiveness in countering well-known cyberattacks while fulfilling its intended objectives. The performance evaluation of the implementation further validates its feasibility and stability, particularly as the volume of evidence associated with animal identities increases. All the infrastructure components, along with detailed deployment instructions, are publicly available as open-source libraries on GitHub, promoting transparency and community-driven development for wider public benefit.