Federated-LSTM based Network Intrusion Detection Method for Intelligent Connected Vehicles

Abstract

Internet of Vehicles (IoV) has enabled intelligent services for connected vehicles such as advanced driver assistance and autonomous vehicles. However, due to the multiple external communication interfaces, intelligent connected vehicles (ICVs) are vulnerable to malicious network intrusion attacks. The malicious attackers can not only remotely intrude into the in-vehicle networks (IVNs) and control the compromised vehicles, but also invade the neighboring vehicles through IoV. To protect the compromised vehicles from being manipulated, a novel federated long short-term memory (LSTM) neural network-based IVN intrusion detection method is proposed in this paper. Specifically, based on the periodicity of the ID sequence of IVN messages, an LSTM neural network model is built for the incoming message ID prediction, and an ID prediction-based network intrusion detection method is developed subsequently. Moreover, an FL framework working in client-server mode is built for secure and efficient LSTM neural network model training in IoV systems. In the framework, ICVs work as the clients for local model training, and base stations (BSs) equipped with mobile edge computing (MEC) servers are the parameter servers for global model parameter aggregation. Simulations have been conducted based on the practical dataset. The numerical results indicate that the detection accuracy of the federated-LSTM based method on spoofing, replay, drop, and DoS attacks is beyond 90%.