Abstract
Explores the fundamental aspects of federated learning (FL) in the context of intrusion detection systems (IDS) within Internet of Things (IoT) networks. Federated learning presents an innovative approach to training machine learning models on distributed devices, thereby minimizing the need to transmit sensitive data to central servers. We classify FL into horizontal, vertical, and federated transfer learning and examine their application in IDS systems. Additionally, we analyze the network structure of FL, encompassing centralized and decentralized FL. Based on the conducted review, it can be concluded that FL holds promise for enhancing data privacy and anomaly detection efficiency in IoT networks.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call