A Novel Intrusion Detection Scheme Using Cloud Grey Wolf Optimizer

In order to solve the problems of low detection efficiency caused by the lack of sufficient training set and dynamic change of attacks. A new adaptive and effective method of industrial control network intrusion detection model is proposed, namely, semi-supervised intrusion detection model optimized by a cloud grey wolf optimization (CGWO) algorithm, which takes into account the balance of the exploration and exploitation abilities, simultaneously do parameter setting for semi-supervised learning and the one-class support vector machine. In the training stage utilize semi-supervised learning algorithm modified by the CGWO to obtain a large-scale training dataset by using a few of label data, according to the characteristics of the industrial control network layer data. The performance of the proposed method has been evaluated demonstrable efficiently and reliably by a comparison and analysis of the simulation, in terms of having a high detection rate and a low false alarm rate without feature selection.