Search Results (434)

Federated learning lets organizations train a shared model without pooling private data. The standard method, Federated Averaging, requires all participants to use the same input features, a condition that fails in cross-sector phishing detection, where banks analyze URL structure and hospitals analyze email content. We present RankBridge, a system that groups participants by comparing ranked lists of SHapley Additive exPlanations (SHAP) feature importance rather than model weights or gradients. Each participant trains a local LightGBM model, extracts the top-K features by SHAP importance, and sends a 60-byte ranked list of feature indices to a central server. The server applies rank correlation and Ward’s hierarchical clustering to identify similarly threatened organizations. RankBridge operates in two modes: ModelShare, where models are also shared within each discovered group for prediction ensembling, and RankOnly, where the server returns only a group label and each participant keeps their model private. Across 32 participants in five organization types, RankBridge (ModelShare) achieves F1 $=0.853$ (AUC $=0.926$) on synthetic data and F1 $=0.772$ (AUC $=0.812$) on real phishing data, and it is the only method to outperform isolated local training on both. On real heterogeneous data the standard baselines adapted to LightGBM, including Federated Averaging, retain a moderate thresholded F1 (≈0.73) but their ranking quality collapses to near-random (AUC $\approx 0.59$, PR-AUC $\approx 0.66$), whereas RankBridge sustains AUC $=0.812$ and PR-AUC $=0.819$. RankBridge recovers the correct organizational groupings with Normalized Mutual Information (NMI) $=0.973$. The rank-based grouping channel itself transmits 60 bytes per participant per round, roughly 10,000× less than a full model upload. Full article

We present S2VDT, a two-party secure vertical decision tree framework built on a suite of matrix-level secure operators, including matrix multiplication, the Hadamard product, reciprocal, and vector comparison. These operators, constructed from additive secret sharing and masked matrices, provide two core advantages. First, inherent parallelism: by casting Gini impurity evaluation and split selection into matrix form, all candidate splits are evaluated simultaneously within a constant number of communication rounds, eliminating the per-split sequential interactions of prior schemes. Second, composable security: each operator is proven secure under the semihonest model via the universal composability framework, and the full training protocol achieves bounded privacy guarantees without relying on homomorphic encryption or an online trusted third party. Experiments on three real-world UCI datasets show that S2VDT matches non-private accuracy with negligible model-level precision loss while reducing communication overhead by $2.5\times$–$7.1\times$ and peak memory consumption by $19\times$–$68\times$ over Pivot. Full article

Patient safety remains a global priority, with surgical errors, including in-hospital infections, procedural mishaps, and delays in diagnosis or treatment, causing over 7 million adverse events and 1 million deaths annually. This study evaluates machine learning (ML) to predict the risk of medical errors in the general surgery department of a Greek tertiary university hospital. Medical error risk was operationalized using several proxy indicators derived from prolonged hospitalization and elevated treatment costs, validated against diagnosis-related complication codes. Using a 10-year dataset of 19,965 anonymized patient records (13.5% error cases, n = 2700), we applied ensemble ML algorithms via WEKA, achieving 94.3% accuracy (Random Forest) in detecting errors such as healthcare-associated infections (HAIs), medication errors, and equipment failures. Given the clinical importance of minimizing missed adverse events, model evaluation prioritized both sensitivity and AUC-ROC in addition to overall accuracy. Key predictors were hospitalization duration (ranked #1 via information gain) and initial diagnosis, enabling early risk flagging (e.g., post-op day 5). Further exploratory analyses excluding hospitalization duration from the predictor set demonstrated a moderate reduction in predictive performance while preserving clinically meaningful discriminative capability, suggesting that model performance was not exclusively dependent on hospitalization duration. Compared to US benchmarks like ACS NSQIP (90% accuracy), our model outperformed by 4.3%, filling a gap in EU/Greek studies amid data silos and resource constraints. Integration with tools like the WHO Surgical Safety Checklist could enable proactive interventions, such as enhanced monitoring for prolonged stays. However, the proposed framework should be interpreted as identifying high adverse-event risk patterns rather than directly detecting clinically adjudicated preventable medical errors. Limitations include retrospective biases and workflow integration challenges; ethical issues like data privacy and algorithmic fairness were addressed via anonymization and ethics approval. Future work will focus on multi-center validation, calibration analysis, longitudinal modeling, and integration of explainable artificial intelligence (XAI) techniques to improve transparency and clinical trust. By blending ML with clinician expertise, this approach shifts healthcare from reactive to proactive error mitigation, improving outcomes and reducing costs. Full article

In this work, the newly developed functional bootstrapping (FBT) for the Cheon–Kim–Kim–Song (CKKS) scheme is used for the first time to homomorphically evaluate an encrypted neural network. The advantage of FBT over previous approaches for the homomorphic evaluation of non-linear activation functions is that it combines bootstrapping and homomorphic function evaluation. For this purpose, FBT for CKKS is extended to be applied to real input values by evaluating the first order Hermite interpolation function not only on its interpolation points but on the entire domain $[0,1]$. For the sigmoid function, to respect the internal representation of negative values in CKKS and the convergence behaviour of trigonometric interpolation, a glueing of shifted and reflected sigmoid functions that is periodic and continuous is used as an input function for FBT. The experimental results yield an accuracy of 97.33% with a relative loss of $0\%$ compared to the Hermite plaintext counterpart that were obtained with a fully connected neural network with 100 hidden neurons on the MNIST test set at a security level of 128 bits. The current implementation required approximately 1.66 s per image (amortised time) and about 201 GB RAM. Full article

As the Internet of Things (IoT) grows, strong, scalable, and adaptive intrusion detection systems (IDS) become increasingly critical for protecting IoT environments. This paper presents a comprehensive and systematic survey of IDS techniques for IoT environments, covering literature from 2021 to early 2026. The review introduces a multidimensional taxonomy that categorizes IDS approaches by detection strategy, learning paradigm, deployment architecture, and evaluation methodology. We examine conventional techniques, such as signature-based and anomaly-based detection, as well as modern machine-learning and deep-learning approaches. Furthermore, emerging paradigms, including Federated Learning, Explainable AI (XAI), TinyML, Large Language Models (LLMs), Transformer, Quantum Machine Learning, Generative Adversarial Networks and Incremental Learning, are analyzed with respect to their applicability to resource-constrained IoT environments. The paper also provides a detailed analysis of publicly available IDS datasets, validation protocols, and evaluation metrics used for benchmarking detection systems. In addition, critical challenges, including dataset realism, adversarial robustness, scalability, privacy preservation, and ethical considerations, are discussed. Finally, we highlight open research directions and propose guidelines for designing next-generation, trustworthy, and scalable IDS frameworks for IoT networks. Full article

Federated Learning (FL) is a machine learning technique that preserves data privacy and security by training models directly on decentralized edge network devices. This generates substantial communication overhead due to the repeated exchange of model updates across numerous edge network devices. Quantization has tackled this challenge by reducing communication overhead and computational costs by quantizing model updates. Although selecting the most suitable quantization level to balance communication efficiency and model accuracy is challenging, failing to achieve this balance results in excessive compression, leading to accuracy degradation due to the lossy nature of the quantization technique. This challenge was tackled in this paper via a Quantile-based lossless compression method named Pcodec, which implements lossless compression in the FL context. Pcodec is a Quantile-based lossless compression algorithm designed for numerical data that utilizes mode identification with delta encoding and binning, where binning groups similar values into entropy-coded bins and stores the exact offset within each bin, thus achieving high compression ratios and efficient processing speed. Using MNIST and CIFAR-10 datasets and models such as CNN and ResNet18, we demonstrate that Pcodec achieves up to 58.19% size reduction with no accuracy loss compared to standard quantization methods. The experiments showed that the proposed Quantile-based compression approach in FL reduces up to 2.81× the communication overhead between each server and edge network device while maintaining the accuracy. In comparison to quantization, the Quantile approach reduced the communication overhead by 2.74×, tackling the main challenge of FL context by reducing communication overhead with a remarkably high compression ratio while maintaining the model’s accuracy. Full article

Behavioral authentication (BA) systems verify user identity claims based on unique behavioral characteristics using machine learning (ML)-based classifiers trained on user behavioral profiles. Although effective, ML-based BA systems face serious privacy threats, including profile inference and reconstruction attacks. This paper presents RUIP-BA (Renewable, Unlinkable, and Irreversible Privacy-Preserving Behavioral Authentication), a non-cryptographic framework designed for settings where computational resources may be limited. Random Projection (RP) maps behavioral profiles into lower-dimensional protected templates while approximately preserving utility-relevant geometry, and local Differential Privacy (DP) injects calibrated stochastic perturbations to provide formal privacy protection. The proposed design jointly targets the ISO/IEC 24745 requirements of renewability, unlinkability, and irreversibility. We provide complete algorithmic realizations for enrollment, verification, template renewal, unlinkability testing, and GAN-based adversarial privacy evaluation. We also introduce rigorous formal privacy derivations and proofs under explicit assumptions, including formal security games, information-theoretic theorem-level guarantees, Cramér–Rao lower bounds for irreversibility, full Jensen–Shannon divergence derivations for unlinkability, and a GAN Nash-equilibrium attack bound. Comprehensive dimensionality ablation across all three modalities confirms robust utility at compact template sizes, and an expanded analysis of the privacy–utility trade-off under varying $ϵ$ values is provided. Experiments on voice, swipe, and drawing datasets show authentication accuracy above $96\%$ while sharply limiting feature recoverability under strong GAN-based attacks. All reported FAR/FRR figures are single-session best-case estimates; cross-session longitudinal evaluation remains future work. RUIP-BA provides a scalable, mathematically grounded, and deployment-ready privacy-preserving BA solution. Full article

Healthcare analytics is often limited by data silos and strict privacy requirements, which make it difficult to share patient-level records across organisations and to build robust predictive models. Federated learning (FL) provides an alternative by keeping data local and exchanging model updates instead of raw records. However, many existing FL solutions remain difficult to deploy in healthcare settings, as they provide limited support for auditability, governance-oriented evidence, and system-level transparency. This paper presents MediVault, an auditable and security-aware federated learning-based system for privacy-preserving healthcare collaboration. MediVault combines round-based federated training, prototype-level protected update exchange, audit-ready telemetry, and an interactive dashboard that exposes non-sensitive evidence of collaboration, model progress, and protocol execution. In addition, the system supports controlled reporting to improve stakeholder communication during pilot deployments. We evaluate MediVault on two public healthcare classification datasets, Breast Cancer Wisconsin (Diagnostic) and Heart Disease, under IID and label-skewed Non-IID settings. Experiments are conducted using logistic regression, linear SVM, and an additional lightweight MLP under matched settings. The observed results suggest that federated training remains competitive with centralised training under the evaluated settings. A prototype-level overhead analysis further shows that protected update exchange introduces measurable computational and communication costs, especially for larger update vectors. These findings indicate that MediVault can support initial system-level validation of auditable, privacy-preserving healthcare FL workflows, while further work is needed for larger-scale deployment, stronger adversarial evaluation, and real-world clinical validation. Full article

The optimisation design of agricultural machinery is shifting from offline, experience-driven engineering towards adaptive, data-driven, and closed-loop intelligent optimisation. Conventional approaches based on computer-aided engineering (CAE), empirical testing, mathematical modelling, and static multi-objective optimisation have provided an important engineering foundation, but they remain limited under unstructured field conditions involving soil heterogeneity, crop variability, climatic disturbance, and nonlinear machinery–environment interactions. This review systematically examines the evolution of intelligent optimisation design for agricultural machinery from conventional simulation-based methods to artificial intelligence (AI)- and digital twin (DT)-enabled paradigms. First, mathematical modelling, response surface methodology, discrete element method (DEM), computational fluid dynamics (CFD), multi-body dynamics (MBD), heuristic algorithms, and early AI-assisted surrogate optimisation are reviewed to clarify their contributions and limitations. Second, frontier enabling technologies are analysed, including agriculture-specific large models, generative AI, lightweight edge intelligence, deep reinforcement learning (DRL), embodied AI, federated learning (FL), and privacy-preserving computing. Third, system-level applications integrating DT and AI are discussed, with emphasis on full-lifecycle machinery optimisation, device–edge–cloud collaborative control, multi-agent fleet coordination, predictive maintenance, and Agriculture 5.0-oriented intelligent equipment systems. Key deployment bottlenecks are further identified, including sim-to-real inconsistency, virtual–physical mismatch in DTs, edge-side trade-offs among accuracy, latency, energy consumption, and cost, insufficient validation standards, and economic adoption barriers. Finally, a 2025–2030 roadmap is proposed, highlighting large-model–DT closed loops, control biomimetics, green low-carbon optimisation, and trustworthy human–machine symbiosis for sustainable Agriculture 5.0. Full article

The present paper suggests a federated learning-based distributed solar forecasting model based on gated recurrent unit (GRU) networks (FL-GRU) to smart buildings in Muscat, Oman. The growing adoption of rooftop photovoltaic (PV) systems in urban settings needs precise, privatizing, and scalable forecasting models able to manage geographically dispersed and statistically heterogeneous data. The suggested solution will include federated learning and GRU networks to train a global forecasting model across several smart buildings and avoid the exchange of raw energy data to overcome these challenges. The local GRU models are trained on local PV generation data and only parameters of the model are relayed to a central aggregation server. This provides privacy of data without compromising the effectiveness of collaborative learning. The proposed framework is tested in a variety of realistic scenarios such as scalability analysis, non-identically distributed (non-IID) data, client dropout, communication constraints, seasonal variability, and privacy saving noise injection. Simulation outcomes show that the proposed FL-GRU model presents a final RMSE of 0.129, MAE of 0.100 and forecasting accuracy of 97%. When increasing the number of clients involved in the process, 2 to 10, RMSE decreases to 0.129, which supports the high scalability advantages. In non-IID scenarios, RMSE ranges between 0.129 and 0.167, and even with half of the clients dropping, the system is robust with an RMSE of 0.172. The proposed FL-GRU is better than the benchmark models, Local GRU, centralized GRU, FL-LSTM, and FL-ANN with a maximum improvement of 22.29% in RMSE reduction. Also, the best predictive consistency is found with correlation analysis with R² = 0.957. On the whole, the suggested approach can offer an efficient, privacy-aware, and scalable solution to distributed solar energy prediction in smart cities. Full article

The growing prevalence of encrypted network traffic has rendered traditional payload-based inspection ineffective, shifting attention toward flow-level statistical analysis combined with machine learning. At the same time, privacy regulations and distributed network architectures make centralised data collection increasingly impractical, motivating federated learning as a privacy-preserving alternative. Despite its promise, deploying federated learning for encrypted traffic classification in realistic environments remains challenging, particularly under heterogeneous client data distributions that arise when different network sites observe different subsets of services. This paper examines how server-side aggregation affects federated QUIC traffic classification under such heterogeneous conditions. We use a five-class Google QUIC dataset and represent each flow with eight statistical features derived from packet size and timing. We compare a centralised baseline with federated learning under three client partitions: mixed-label clients (C1), service-based single-class clients (C2), and hash-based semi-IID clients (C3). For each case, we evaluate four Flower aggregation strategies: FedAvg, FedAdam, FedAvgM, and FedYogi. Results show that client distribution has a greater impact on performance than the choice of aggregation strategy. Federated models match or closely approach centralised performance in C1 and C3, with accuracy up to 0.9969 and macro-AUC near 1.0. In C2, accuracy drops due to extreme label skew, but adaptive aggregation mitigates the effect. FedYogi achieves the best C2 accuracy of 0.9287, while FedAvgM attains the highest C2 macro-AUC of 0.9885. ROC curves and confusion matrices confirm that the choice of aggregation matters mainly under severe heterogeneity. Full article

Federated learning is a distributed machine learning paradigm that enables multiple devices to collaboratively train a shared model while keeping their raw data localized. Federated learning has become an attractive solution for intrusion detection in Internet of Things (IoT)-based wireless sensor networks because it enables collaborative model training without transferring raw traffic data. However, real deployments rarely satisfy the common assumption that client data are independent and identically distributed (IID). In practical wireless sensor networks, data heterogeneity naturally arises from spatial variation, uneven attack exposure, traffic imbalance, and differences in sensing conditions, which can substantially affect detection reliability and deployment feasibility. This study presents an application-oriented evaluation of federated intrusion detection under controlled non-IID conditions using three representative datasets: WSN-DS, CIC-IDS-2017, and UNSW-NB15. An LSTM-based intrusion detection model is trained in a federated setting and assessed using three aggregation strategies, namely, FedAvg, FedProx, and SCAFFOLD, under label skew, quantity skew, and feature skew scenarios. The results show that standard FedAvg degrades markedly as heterogeneity increases, with accuracy reductions of up to 23.4 percentage points and substantially higher communication cost under extreme non-IID settings. In contrast, FedProx and SCAFFOLD improve convergence stability and reduce the impact of client drift, with SCAFFOLD showing the strongest overall robustness and up to 45% lower communication cost than FedAvg due to faster convergence. These results demonstrate that non-IID awareness is essential for building deployable privacy-preserving intrusion detection systems for resource-constrained IoT environments. The study provides practical guidance for selecting federated aggregation strategies in wireless sensor network security applications where robustness, bandwidth efficiency, and real-world data heterogeneity must be jointly considered. Full article

Connected and autonomous vehicles (CAVs) increasingly rely on vehicle-to-everything (V2X) communication and distributed sensing infrastructures to support cooperative driving and intelligent transportation services. While these capabilities improve traffic efficiency and safety, they also expand the attack surface of vehicular networks and expose in-vehicle communication systems such as the Controller Area Network (CAN) bus to a wide range of cyber threats. Machine learning-based anomaly detection has emerged as a promising approach for identifying malicious CAN traffic patterns; however, conventional centralized learning requires large-scale data aggregation from vehicles, which raises privacy and scalability concerns. Federated learning (FL) enables collaborative model training across distributed vehicles without requiring the exchange of raw in-vehicle data, making it attractive for privacy-preserving vehicular security applications. Nevertheless, FL systems remain vulnerable to adversarial participants that manipulate local training data or model updates to poison the global model during aggregation. In this work, we present a systematic robustness evaluation of federated anomaly detection in connected vehicular networks under adversarial conditions. The study compares six aggregation strategies, including Federated Averaging (FedAvg), coordinate-wise Median, Trimmed Mean, Krum, Multi-Krum, and Geometric Median (GeoMed), within a non-IID federated CAN bus anomaly detection setting. The evaluation covers label-flipping attacks, gradient-scaling attacks, and a feature-triggered backdoor attack. In addition, the analysis examines malicious client participation, attack-strength variation, learning-rate sensitivity, Trimmed Mean beta sensitivity, multi-seed reliability, and server-side aggregation time. The results show that FedAvg is vulnerable under strong adversarial manipulation, while Trimmed Mean is sensitive to the selected trimming fraction. Median and GeoMed provide strong robustness against gradient-scaling attacks, whereas Multi-Krum achieves the strongest resistance to label-flipping and backdoor attacks. These findings demonstrate that no single aggregation strategy is optimal across all threat models. Instead, robust aggregation for federated CAV anomaly detection should be selected according to the expected attack type, reliability requirement, and computational overhead. Full article

The standardisation of post-quantum cryptography (PQC) by NIST marks a critical transition away from classical public-key schemes towards quantum-resistant successors. As machine learning (ML) applications proliferate, the demand for efficient cryptographic primitives intensifies, requiring implementations that are simultaneously quantum-safe and resource-aware. Recent surveys have investigated the interplay between ML and PQC, with particular focus on ML-assisted parameter optimisation, privacy-preserving ML leveraging lattice-based cryptography, and neural-network implementations of quantum-resistant algorithms. Building on these findings, we propose QSafe-ML, a comprehensive four-stage framework that integrates hardware profiling, surrogate modelling via ML, constrained multi-objective optimisation, and continuous security validation to facilitate the tuning of PQC parameters and implementations. The framework targets NIST-standardised lattice-based schemes CRYSTALS-Kyber, CRYSTALS-Dilithium, Falcon, and NTRU across three heterogeneous hardware platforms. Experimental evaluation with $n=30$ repeated trials demonstrates mean latency reductions of 27.5–41.9% (95% CI ±1.1–1.7 pp), memory savings of 13.3–30.2%, and energy savings of 22.8–38.2% over NIST reference baselines, with all configurations maintaining ≥128-bit post-quantum security. An ablation study confirms that surrogate-guided search accounts for the dominant share of these gains. All code, data, and benchmark instructions are released at a public repository (available upon acceptance of this manuscript) to promote reproducibility in evaluating ML-assisted cryptographic systems. Full article

Handover optimization is essential for seamless connectivity in 5G and beyond networks. Existing approaches present fundamental challenges of centralized solutions achieving coordination and accuracy but creating privacy risks under the General Data Protection Regulation (GDPR), while distributed privacy-preserving approaches protect user data but lack the network-wide visibility necessary for optimal mobility decisions. This systematic review synthesizes 49 peer-reviewed studies published between 2010 and 2025, identified through a PRISMA-compliant search across IEEE Xplore, ScienceDirect, SpringerLink, MDPI, ACM Digital Library, and Google Scholar. Eligible studies addressed cellular handover or mobility management using traditional signal-based, Machine Learning, Federated Learning, Software-Defined Networking strategies, and reported quantitative performance metrics. A structured quality assessment evaluated methodological rigor, dataset validation, benchmarking practices, handover-specific metrics, and scalability. Synthesis evidence shows that existing approaches do not simultaneously satisfy critical requirements for next-generation mobility management of accuracy, privacy, scalability, and real-time network-wide coordination. Machine learning achieves high accuracy (up to 97%) but depends on centralized data; Reinforcement Learning supports real-time adaptation but incurs high computational costs; federated learning preserve privacy but suffers from limited global coordination; and software-defined networking enables centralized control but requires continuous transmission of raw data. Evidence quality is further limited to simulation-based assessments and limited real-world datasets. Overall, the reviews identify a clear evolution from reactive threshold-based methods towards proactive prediction and highlights the need for unified, privacy-preserving and globally coordinated handover frameworks. The findings point toward integrating federated learning with Software-Defined Mobile Networking as promising architectural direction for 6G mobility management. Full article