Federated Learning Approach for Distributed <scp>DDoS</scp> Detection in <scp>VANETs</scp>

ABSTRACT Vehicular Ad Hoc Networks (VANETs), a crucial part of Intelligent Transportation Systems, provide real‐time vehicle‐RSU communication. VANETs are subject to DDoS assaults, which may undermine safety‐critical systems due to their dynamic and dispersed nature. VANET DDoS detection solutions frequently use centralized designs that need raw data aggregation (DA), which causes scalability, communication cost, and privacy difficulties. Additionally, traditional models fail to adapt to vehicular surroundings' varied and frequently changing traffic patterns. Federated Anomaly Detection with Personalized Autoencoders (FAD‐PAE) is proposed to address these issues. Vehicles and roadside equipment train lightweight Autoencoders (AE) locally to simulate regular traffic behavior, exchanging just model updates via federated learning. Personalized fine‐tuning at each node adapts to local traffic changes, while safe and strong aggregation protects against compromised clients. The VANET‐based cooperative and privacy‐preserving DDoS detection approach reduces false alarms and communication costs. Experimental results show superior detection accuracy (ACC), reaction speed, and flexibility compared to centralized techniques.