A Survey on Privacy-Preserving Federated Learning in Internet of Things (IoT)
S. Raghav, B. Vamsi Krishna, Ch. Vanipriya · 2025
This survey article provides a comprehensive overview of Privacy-preserving Federated Learning (FL) in the Internet of Things (IoT), focusing on secure collaborative learning with distributed data. In response to the proliferation of IoT devices generating vast amounts of sensitive information, the survey delves into state-of-the-art methodologies and technologies aimed at preserving user privacy during collaborative model training. The review encompasses cryptographic techniques, secure aggregation protocols, and differential privacy mechanisms, addressing the unique challenges posed by decentralized and heterogeneous IoT environments. Through an analysis of communication overhead, resource constraints, and device diversity, the survey offers a nuanced understanding of the current landscape, including optimization strategies and emerging trends. Serving as a valuable resource for researchers and practitioners, this survey not only synthesizes existing knowledge but also identifies research gaps and proposes potential directions for advancing secure collaborative learning in IoT through Privacy-Preserving Federated Learning.