An Extensive Overview of anamoly Detection Analysis in FL-Based IDS

In this paper, we present a Federated Learning-based Intrusion Detection System (FL-IDS) aimed at enhancing security in Connected Autonomous Vehicles (CAVs) within IoT environments. The novelty lies in the dual utilization of Support Vector Machine (SVM) and Convolutional Neural Networks (CNN) for anomaly detection, leveraging the Flower framework for privacy-preserving, decentralized model training. Unlike traditional centralized approaches, FL-IDS ensures data confidentiality by sharing only model updates. Using the NSL-KDD dataset, our evaluation highlights superior accuracy and loss metrics, validating the efficiency of both machine learning and deep learning methods for detecting DDoS, Probe, and U2R attacks. This work contributes to the advancement of secure and efficient vehicular communication systems, providing scalable solutions for real-world IoT deployments.