Machine Learning-Enhanced DDoS Attack Detection and Mitigation in VANET Infrastructure

Abstract

Vehicular ad-hoc networks (VANETs) are crucial for road safety, traffic management, and intelligent transportation systems, but they are vulnerable to Distributed Denial of Service (DDoS) attacks, which can severely disrupt communication between vehicles and Roadside Units (RSUs). Traditional DDoS detection methods in VANETs are often inefficient due to reliance on centralized architectures and handcrafted features. To address these challenges, we propose the Hybrid Deep Learning with Federated Learning (HDL-FL) framework, which leverages Convolutional Neural Networks (CNNs) to capture spatial and temporal traffic patterns. By utilizing Federated Learning, HDL-FL enables distributed, privacy-preserving training across RSUs and vehicles while reducing communication overhead. Experimental evaluations in simulated VANET environments show that HDL-FL achieves a 94% improvement in accuracy, a 30% reduction in false positives, and a 99% increase in attack detection rate while also reducing communication overhead by 6.5 s and latency by 160 ms. The framework offers a scalable, robust, and privacy-preserving solution for securing next-generation Vehicle-to-Everything (V2X) infrastructures, outperforming traditional models in terms of spatio-temporal accuracy and scalability. For performance validation, the HDL-FL framework is compared with baseline models, including traditional machine learning approaches such as Support Vector Machine, AI, and IoT.