The Internet's and smart devices' rapid development causes an increase in network traffic, which makes the infrastructure more complex and heterogeneous. Mobile phones, wearable technology, and driverless vehicles are examples of distributed networks that produce enormous amounts of data daily. Security and privacy of such devices are significantly enhanced by intrusion detection systems. Due to the rapid evolution in the volume and variety of security threats for such systems, intrusion detection for such paradigms is a non-trivial task that has gained additional significance. Yet, intrusion detection for IIoT is a challenge that necessitates taking into account the trade-off between detection accuracy and performance overheads due to the specific characteristics of such systems, i.e., battery power, bandwidth and CPU overheads, and network dynamics. Federated learning (FL), which trains models locally and sends the parameters to a centralized server, is an appropriate example of a decentralized learning technique that respects privacy. The purpose of the current research is to give a thorough and in-depth analysis of the application of FL-based intrusion detection systems for IIoT.

Federated Learning, Intrusion Detected Systems, Industrial Internet of Things, Internet of Things, Differential Privacy Preservation, Security.