The trend of the next generation of the internet has already been scrutinized by top analytics enterprises. According to Gartner investigations, it is predicted that, by 2024, 75% of the global population will have their personal data covered under privacy regulations. This alarming statistic necessitates the orchestration of several security components to address the enormous challenges posed by federated and distributed learning environments. Federated learning (FL) is a promising technique that allows multiple parties to collaboratively train a model without sharing their data. However, even though FL is seen as a privacy-preserving distributed machine learning method, recent works have demonstrated that FL is vulnerable to some privacy attacks. Homomorphic encryption (HE) and differential privacy (DP) are two promising techniques that can be used to address these privacy concerns. HE allows secure computations on encrypted data, while DP provides strong privacy guarantees by adding noise to the data. This paper first presents consistent attacks on privacy in federated learning and then provides an overview of HE and DP techniques for secure federated learning in next-generation internet applications. It discusses the strengths and weaknesses of these techniques in different settings as described in the literature, with a particular focus on the trade-off between privacy and convergence, as well as the computation overheads involved. The objective of this paper is to analyze the challenges associated with each technique and identify potential opportunities and solutions for designing a more robust, privacy-preserving federated learning framework.

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.