Title: Few-shot learning-based zero-day anomaly detection in vehicular networks using conditional GANs

Authors: Haewon Byeon; Mohammed E. Seno; Aadam Quraishi; Azzah AlGhamdi; Mukesh Soni; Ihtiram Raza Khan; Mohammad Shabaz

Addresses: Convergence Department, Korea University of Technology and Education, Cheonan, South Korea ' Department of Computer Sciences, College of Sciences, University of Al Maarif, Al Anbar, 31001, Iraq ' M.D. Research, Intervention Treatment Institute, Houston, Texas, USA ' Computer Information Systems Department, College of Computer Science and Information Technology, Imam Abdalrhman Bin Faisal University, Khobar, Saudi Arabia ' Dr. D.Y. Patil Vidyapeeth, Pune, Dr. D. Y. Patil School of Science and Technology, Tathawade, Pune, India ' Computer Science Department, Jamia Hamdard Delhi, India ' Model Institute of Engineering and Technology, Jammu, J&K, India

Abstract: Detecting zero-day anomalies in vehicular networks poses significant challenges due to the lack of attack data. Anomaly-based detection methods are commonly used; however, complex and dynamic environments in vehicular ad hoc networks (VANETs) lead to diverse behavioural patterns, increasing the likelihood of high false alarm rates. This study proposes a few-shot learning-based zero-day anomaly detection method for vehicular networks using conditional generative adversarial networks (GANs). The proposed approach introduces a conditional GAN model with multiple generators and discriminators to enhance anomaly detection capabilities. To address data imbalance caused by the limited availability of attack samples, a collaborative focal loss function is incorporated into the discriminator to focus on hard-to-classify anomalies. Extensive experiments conducted on the F2MD vehicular network simulation platform demonstrate that the proposed method outperforms existing approaches in terms of detection accuracy and latency for zero-day anomalies. This provides an effective solution for enhancing anomaly detection in vehicular networks.

Keywords: VANETS; anomaly detection; zero-day anomalies; few-shot learning; conditional generative adversarial networks; GANs.

DOI: 10.1504/IJIIDS.2026.155297

International Journal of Intelligent Information and Database Systems, 2026 Vol.18 No.3/4, pp.504 - 527

Received: 17 Jan 2025
Accepted: 07 Mar 2025
Published online: 30 Jul 2026 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article