Autonomous Systems in the Internet of Vehicles
by Balamurugan Balusamy, Sandeep Kumar Mathivanan, Prabhu Jayagopal, S. K. B. Sangeetha, Ali Kashif Bashir
12Federated Autoencoder-GRU–Based Intrusion Detection System for Secure IoV-Connected Autonomous Vehicles
Pegadapelli Srinivas1, Vijey Nathan2, Radhika Rajavelu3, Suresh Kulandaivelu3* and Roger Atanga4
1Department of Computer Science and Engineering, Bharatiya Engineering Science & Technology Innovation University, AP, India
2Department of Computer Science and Engineering, TRP Engineering College, Trichy, India
3School of Computing Science and Engineering, Galgotias University, Greater Noida, India
4Department of Pharmacology and Technology, University of Arizona College of Pharmacy, Tucson, Azirona, USA
Abstract
Internet of Vehicles (IoV)–enabled autonomous vehicles present a critical cybersecurity problem in the sense that centralized intrusion detection system (IDS) can potentially disclose personal information and cause communication delay. Traditional IDS models find it difficult to cope with the changing patterns of threats. The study suggests a federated deep learning IDS using an autoencodergated recurrent unit (GRU) model that preserves data confidentiality between nodes while learning distributed representations of vehicular network traffic. Whereas the GRU carries out sequential patterns for classification, the autoencoder monitors feature compression. Experimental evaluation in a simulated IoV environment using the CARLA simulator and synthetic vehicular traffic data demonstrated that the proposed federated autoencoder-GRU IDS significantly outperforms traditional ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access