Resource-Efficient Ensemble Learning for Edge IIoT Network Security Against OSINT-Based Attacks

The rise of Edge IIoT networks has transformed industries by enabling real-time data processing, but these networks face significant c ybersecurity risks, particularly from OSINT-based attacks. This paper presents a resource-efficient ensemble learning framework designed to detect such attacks in Edge IIoT environments. The framework integrates machine learning models, including RandomForest, K-Nearest Neighbors, and Logistic Regression, optimized with Principal Component Analysis (PCA) to reduce data dimensionality and computational overhead. GridSearchCV and StratifiedKFold cross-validation were employed to fine-tune the models, resulting in high detection accuracy. This approach ensures robust and efficient security for resource-constrained Edge IIoT networks.