A Robust Cybersecurity for Smart Grids: Multi-Attack Detection Using Hybrid Ensemble Models on Realistic Datasets

This project aims to enhance the cybersecurity of smart grids by developing a robust system for detecting multiple types of cyberattacks using a hybrid ensemble approach. The system integrates multiple machine learning models, such as Random Forest and XGBoost, to classify network traffic and identify anomalies. The ensemble model is trained on realistic datasets, combining traditional attack detection with advanced anomaly detection techniques like Isolation Forest and One-Class SVM. The project focuses on improving detection accuracy and minimizing false positives, making it suitable for real-time threat detection in smart grid infrastructures. By leveraging hybrid ensemble models, the system can effectively detect a wide range of attacks, including Distributed Denial of Service (DDoS), Port Scan, and other sophisticated cyber threats targeting smart grids.