Smart Industry Anomaly Detection Dataset for Cyber-Physical Threat Monitoring in Industrial IoT Environment

The objective of this project is to develop a machine learning-based system for detecting and classifying cyber-physical threats in Industrial IoT (IIoT) environments. The system aims to identify five types of attacks—Normal, Probing, Denial of Service (DoS), User to Root (U2R), and Remote to Local (R2L)—by analyzing network traffic data with 41 features. Utilizing algorithms such as Stacking Classifier and XGBoost, the system is designed to effectively classify and detect anomalies in real-time, enhancing the security of IIoT systems. The project also focuses on evaluating model performance to ensure accurate and reliable threat detection, thereby strengthening the overall security of industrial networks.