Abstract

Industrial Control Systems (ICS) are increasingly vulnerable to cyberattacks, posing significant risks to critical infrastructure. Traditional intrusion detection systems (IDS) often struggle to effectively identify sophisticated threats in ICS environments due to the unique characteristics of network traffic and the evolving threat landscape. This paper proposes a novel hybrid deep learning approach for enhanced intrusion detection in ICS, combining feature selection techniques with ensemble learning. The proposed methodology leverages the strengths of multiple deep learning models, including Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs), to capture both spatial and temporal patterns in network traffic data. Feature selection is employed to identify the most relevant features, reducing dimensionality and improving model performance. The ensemble approach combines the predictions of individual deep learning models to enhance accuracy and robustness. The effectiveness of the proposed methodology is evaluated using a publicly available ICS dataset, demonstrating superior performance compared to existing state-of-the-art intrusion detection techniques. The results highlight the potential of the proposed hybrid deep learning approach to significantly improve the security of ICS environments.