Litcius/Paper detail

Enhancing federated learning for IoT-based anomaly detection: A reputation-based client selection approach

Maha Jawad Alfadhil, Ali Baydoun, Moutaz Alazab, Hafeez Ur Rehman, Jihad Jaam, Sumaya Al-Maadeed

2025Alexandria Engineering Journal7 citationsDOIOpen Access PDF

Abstract

Federated Learning (FL) enables collaborative model training across decentralized, privacy-sensitive environments but often suffers from slow convergence, unbalanced client selection, and non‑IID data challenges. We propose a Reputation‑Based Client Selection Mechanism with proportional fairness, computing each client’s reputation from accuracy, consistency, network conditions, data quality, and historical reliability. By adaptively prioritizing high‑contributing clients while ensuring equitable participation, our method accelerates convergence and balances contributions. Evaluations on the UNSW‑NB15 intrusion detection dataset under IID and non‑IID settings demonstrate that our approach significantly reduces the number of communication rounds needed to reach stable accuracy compared to FedAvg and FedProx, while enhancing model generalization and robustness. This scalable strategy advances FL for efficient, inclusive learning in IoT and cybersecurity.

Topics & Concepts

Federated learningComputer scienceScalabilityAnomaly detectionConvergence (economics)ReputationSelection (genetic algorithm)GeneralizationIntrusion detection systemFeature selectionData miningData modelingMachine learningAdaptabilityArtificial intelligenceModel selectionDistributed computingAnomaly (physics)Data sharingIntrusionStability (learning theory)InteroperabilityUsage dataMechanism (biology)Supervised learningPrivacy-Preserving Technologies in DataCryptography and Data SecurityMobile Crowdsensing and Crowdsourcing