The rapid expansion of Internet of Things (IoT) ecosystems has intensified the need for distributed intelligence mechanisms that reduce direct raw-data exposure while remaining resilient to adversarial manipulation. Federated learning (FL) addresses part of this challenge by enabling collaborative model training without centralizing raw data, but it remains vulnerable to malicious client behavior, particularly model poisoning attacks that can substantially degrade global model quality. This paper investigates a blockchain-assisted, trust-aware FL framework for privacy-aware distributed intelligence in resource-constrained IoT systems, where the blockchain layer is used to support trust coordination, auditability, traceability, and tamper-resistant metadata recording rather than to directly improve predictive performance. The empirical study compares six aggregation strategies: FedAvg, coordinate-wise Median, Trimmed Mean, FLTrust, trust-aware weighted aggregation, and a hybrid trust-trimmed mean method. The primary evaluation is conducted on the UCI Human Activity Recognition (UCI HAR) dataset under Dirichlet-based non-IID client partitioning α = 0.1 and α = 1.0, partial client participation, and sign-flip model poisoning. Each configuration is evaluated over five independent runs. Under the severe 40% malicious-client stress test, FLTrust achieves the strongest mean robustness among the evaluated methods, reaching 0.4195 ± 0.1295 accuracy and 0.3108 ± 0.1294 macro-F1 for α = 0.1, and 0.6472 ± 0.0725 accuracy and 0.6014 ± 0.0949 macro-F1 for α = 1.0. In lower-intensity attack controls with 10% and 20% malicious clients, the trust-aware and hybrid trust-trimmed strategies are the most competitive, achieving the highest or near-highest mean performance without requiring a clean server-side reference set. Mechanism-level analysis shows that FLTrust is particularly effective in the severe setting because its reference-based scoring assigns near-zero weights to malicious clients, whereas trust-aware and hybrid methods rely on relative update consistency and are more affected by the interaction between poisoning and statistical heterogeneity. Globally, the results indicate that no single aggregation rule dominates all adversarial regimes. Instead, reference-based trust provides strong protection under severe poisoning, while trust-aware and hybrid aggregation offer competitive root-free alternatives under lower attack intensities. The findings also clarify that the privacy-preserving scope of the framework derives from FL-based data locality and does not constitute a formal cryptographic privacy guarantee.
M. Reis, Carlos Serôdio, Frederico Branco· Electronics· 0 citations
Vehicle-to-Everything (V2X) communication systems are becoming a foundational component of intelligent transportation systems, but their increasing connectivity also enlarges the cyberattack surface and raises important privacy and deployment challenges for intrusion detection. Conventional centralized intrusion detection systems can achieve strong predictive performance, yet they require aggregation of sensitive traffic data and may be difficult to deploy across distributed edge environments. This study presents a federated learning-based intrusion detection evaluation framework for privacy-aware and deployment-oriented security monitoring in V2X-inspired distributed environments. Rather than proposing a new detection architecture, the work focuses on a more rigorous and realistic assessment protocol for federated intrusion detection under scenario shift, client heterogeneity, threshold-sensitive operation, and communication constraints. The proposed approach combines group-based train/test partitioning to better reflect scenario separation, lightweight multilayer perceptron (MLP) models suitable for edge-side training, and explicit analysis of communication overhead and threshold calibration. Using the CICIDS2017 dataset as a controlled proxy benchmark, the study compares centralized baselines, local-only learning, FedAvg, and FedProx for binary intrusion detection under approximately IID and strongly non-IID client partitions. The experimental protocol uses equal training-set sizes across centralized and federated methods, an independent calibration set for threshold and checkpoint selection, and five independent random seeds, with results reported as mean ± standard deviation. The results show that the stricter group-based evaluation protocol substantially reduces performance compared with optimistic random-split evaluation, confirming the importance of scenario-aware validation for intrusion detection. Under the protocol, the best mean F1-score was obtained by FedAvg in the strong non-IID configuration, with an F1-score of 0.468 ± 0.028, followed closely by FedAvg under approximately IID partitioning with 0.463 ± 0.036. Centralized MLP, logistic regression, and random forest baselines achieved comparable but slightly lower F1-scores, indicating that federated learning remained competitive rather than clearly superior under this challenging setting. The analysis further shows that threshold calibration on an independent calibration set materially changes the operating point of the detectors, while validation-selected federated checkpoints generally occurred in later communication rounds within the tested 15-round budget. Communication analysis showed that the lightweight MLP required only approximately 72 kB per model update, corresponding to about 720 kB per federated round when both uplink and downlink traffic were counted for five clients. Overall, the findings support federated learning as a viable and communication-efficient direction for privacy-aware intrusion detection in distributed edge-security settings, while also highlighting the need for cautious interpretation, native V2X validation, and future robustness analysis against compromised federated clients.
Federated learning (FL) has emerged as a promising paradigm for enabling distributed intelligence in Internet of Things (IoT) environments while preserving data privacy and reducing the need for centralized data collection. However, the practical deployment of FL in IoT scenarios remains challenging due to heterogeneous data distributions, unreliable communication conditions, and the presence of faulty or malicious edge devices that can disrupt collaborative training. These limitations can significantly degrade convergence stability and predictive performance, particularly in resource-constrained and intermittently connected networks. This paper proposes a simulation-driven trust-aware federated learning framework for robust intelligent IoT networks. The proposed approach incorporates a dynamic trust-based aggregation mechanism that adaptively weights client contributions based on the consistency of their local model updates with the global model state. In addition, a controlled IoT-oriented federated simulation environment is developed to emulate heterogeneous edge conditions, including non-independent and identically distributed (non-IID) data partitioning, adversarial model manipulation, and intermittent client connectivity caused by communication dropouts. Extensive multi-seed experiments were conducted on the UCI Human Activity Recognition (UCI HAR) dataset and complemented with an auxiliary CIFAR-10 convolutional neural network (CNN) validation scenario. The evaluation considered multiple adversarial settings, including sign-flip, Gaussian-noise, scaling, and label-flip attacks, as well as communication-dropout probabilities up to 50%. In contrast with the initial FedAvg-only evaluation, the revised experimental analysis includes comparisons with representative robust aggregation baselines, namely Median, Trimmed Mean, Krum, Multi-Krum, and an auxiliary Bulyan configuration. The experimental results demonstrate that the proposed Trust-FedAvg framework substantially improves robustness over conventional FedAvg and remains competitive with established robust aggregation strategies, particularly under directional model-manipulation attacks and intermittent-connectivity conditions. Under a 20% sign-flip attack on UCI HAR, the proposed method achieved a final test accuracy of 86.2%, whereas conventional FedAvg degraded to approximately 44.7%. Furthermore, under combined adversarial and intermittent-connectivity conditions with 50% communication dropout, Trust-FedAvg maintained a final accuracy of 57.0%, compared with 21.3% for FedAvg, 24.8% for Median, and 14.6% for Trimmed Mean. The additional experiments also show that Trust-FedAvg is not universally superior across all perturbation types: under severe Gaussian-noise attacks, coordinate-wise Median and Multi-Krum provided stronger robustness in some settings. Overall, the results suggest that trust-aware aggregation can improve robustness against unreliable or malicious simulated clients while preserving a relatively simple aggregation procedure. Runtime measurements further indicate that the proposed method introduces only limited round-level overhead compared with FedAvg, while remaining simpler than more complex Byzantine-resilient alternatives. Further validation with real IoT deployments, additional sensor datasets, asynchronous communication models, energy profiling, and communication-overhead measurements is required to fully assess deployment feasibility in real IoT environments. The proposed framework provides a practical, extensible basis for the design and evaluation of resilient AI-enabled IoT networks operating under controlled but practically relevant edge-learning constraints.
M. Reis, Carlos Serôdio, Frederico Branco· Applied Sciences· 0 citations