An enhanced intelligent model: To protect marine IoT sensor environment using ensemble machine learning approach

Abstract

The research in marine sensors and the Internet of Things (IoT) has grown exponentially with the ample warehouse of natural materials in the sea. The growing activities in the marine sensor environment increased the threat of anomalies and cyber-attacks. Many Intrusion Detection Systems (IDS) and classical machine learning-based models have been proposed to secure the sensor-based IoT infrastructure. Still, these mechanisms have failed to achieve significant results for securing the marine sensor environment due to the discriminant requirements of the IoT appliances in deep oceans, such as distribution, information complexity, scalability, higher network bandwidth requirements, and low computational capacity. Hence, we propose a lightweight and robust ensemble model to secure the marine IoT environment from cyber-attacks and malicious activities. This paper established an optimized Light Gradient Boosting Machine (Light-GBM) algorithm for ocean IoT attack detection. The experiments were conducted on Distributed Smart Space Orchestration System (DS2OS) dataset. The proposed methodology includes a label encoding technique for best feature selection, hyper-parameter tuning, ensemble function, and a novel algorithm to develop an ocean IoT attack detection model. As an extension of traditional methods, the optimized Light-GBM model can handle the distributed IoT attacks in the deeper marine environments with low computational cost and with 98.52% detection accuracy. The comparative analysis confirms the effectiveness of the proposed model for marine sensor safety. Conclusively, the proposed model mitigates the threat of cyber-attacks in the marine sensor environment and presenting a promising future in real-time ocean-based IoT applications.