Federated Learning-assisted Distributed Intrusion Detection Using Mesh Satellite Nets for Autonomous Vehicle Protection

The widespread use of intelligent consumer electronics, specifically autonomous vehicles, has exponentially increased. The key enablers of this pervasive are the Internet of Things (IoT), Artificial Intelligence (AI), and Satellite communications, which provide consumers with highly precise and reliable self-driving vehicles. However, autonomous vehicles come also with significant cybersecurity concerns. Attackers can easily use satellite links to launch cyberattacks against autonomous vehicles. An Intrusion Detection System (IDS) is one of the most effective mechanisms for providing secure autonomous vehicles. However, existing IDSs based on machine and deep learning train their models in a centralized server, which uploads data or parameters to the central server for training. This structure of IDS has challenges with vehicle mobility, brings processing delays, and increases privacy and security risks, affecting vehicles’ performance. Therefore, for the first time, this paper proposes a new federated learning-assisted distributed IDS using a mesh satellite net to protect autonomous vehicles. We construct a local model using a deep neural network. Then, we provide a mesh federated learning approach that keeps model training local and lets satellites exchange their parameters in a privacy-preserving way. The simulation results show that our proposed model works well while keeping the computation cost reasonable.