| Title | Privacy-Preserving Federated Learning for Internet of Things: Architecture, Security Challenges, and Future Directions |
| Research Area | Internet of Things |
| Abstract | This paper investigates the application of privacy-preserving federated learning in IoT environments
and proposes a layered conceptual architecture for secure collaborative intelligence. The study
examines the interaction between IoT devices, edge gateways, federated clients, aggregation
servers, privacy mechanisms, and application services. Particular attention is given to non
independent and identically distributed data, device heterogeneity, limited computational resources,
intermittent connectivity, communication efficiency, malicious participants, model poisoning,
inference attacks, and information leakage through model updates. Privacy-enhancing technologies
including differential privacy, secure aggregation, encryption, secure multiparty computation, and
trusted execution environments are discussed as complementary mechanisms rather than isolated
solutions |
| Keywords | Federated Learning, Internet of Things, Privacy Preservation, Edge Computing, Machine Learning, Secure Aggregation, Differential Privacy, IoT Security, Distributed Intelligence |
| Paper Status | Published |
| Volume | 2 |
| Issue | 5 |
| Published On | 09/09/2026 |
| Published File |
IJSRTD_4892.pdf
|