A Hybrid Deep Learning Solution for Real-Time DDoS Mitigation in IIoT Environments
S. Kamaleswari, N. Suganthi · 2024
The Industrial Internet of Things (IIoT) has revolutionized industrial operations by enhancing connectivity and automation. However, this interconnectivity also introduces significant vulnerabilities, particularly to Distributed Denial of Service (DDoS) attacks, which can disrupt critical industrial processes. This proposed model designed to fortify IIoT networks against DDoS threats. The proposed approach employs a hybrid model that integrates CNN and Bi-LSTMs networks to effectively capture spatial and temporal patterns in network traffic data. The framework encompasses including data collection, preprocessing, DDoS detection, and automated strategies. The framework using real-world IIoT traffic datasets, preliminary results prove that the work expressively improves DDoS detection capabilities while maintaining low false positive rates. This work ensuring the reliability and availability of industrial operations. Future research will explore advanced deep learning architectures and the integration of this framework with cutting-edge networking technologies for dynamic threat response.