The research proposes a federated learning framework for intrusion detection in Internet of Vehicles (IOVs) using the CIC-IDS 2017 dataset. The framework uses SMOTE for handling class imbalance, outlier detection for identifying and removing abnormal observations, and hyperparameter tuning to optimize the model’s performance. The framework was evaluated using various performance metrics and was successful in detecting intrusions with other datasets and conventional classifiers. The proposed framework can protect sensitive data while achieving high intrusion detection performance. It represents a significant step in enhancing privacy and security in machine learning.
Publication date: 27 Nov 2023
Project Page: Not provided
Paper: https://arxiv.org/pdf/2311.13800
