Federated Learning-Based Trust Evaluation With Fuzzy Logic for Privacy and Robustness in Fog Computing
Thinh Le Vinh, Tran Thien Huan, Huyen Trang Phan, Samia Bouzefrane · IEEE Access · 2025
Trust evaluation significantly influences security and reliability in fog computing-based Wi-Fi mesh networks. This paper introduces a Federated Learning Trust Model (FLTM) to assess trustworthiness across 2000 resources while preserving data privacy. FLTM incorporates six critical metrics: Availability, Reliability, Data Integrity, Identity, Computational Capability, and Throughput. To address challenges related to unlabeled datasets, fuzzy logic techniques are employed to generate initial trust labels for local neural network training at fog nodes. The key contributions include a privacy-preserving federated learning framework specifically tailored for robust trust evaluation in hierarchical fog computing architectures, robust fuzzy logic-based labeling enhancing interpretability and reliability in the trust assessment process, extensive empirical validations demonstrating superior prediction accuracy, computational efficiency, enhanced privacy preservation, and scalability compared to traditional centralized approaches. Additionally, comprehensive comparative analyses against existing federated learning approaches validated on different datasets, and against non-federated methods using identical datasets, confirm FLTM’s practical advantages. Experimental results validate the robustness, scalability, and suitability of FLTM for real-time trust assessments in distributed fog computing-enabled Wi-Fi mesh networks.