Abstract
The Industrial Internet of Things (IIoT) is used in various industries to achieve industrial automation and intelligence. Therefore, it is important to assess the network security situation of the IIoT. The existing network situation assessment methods do not take into account the particularity of the IIoT’s network security requirements and cannot achieve accurate assessment. In addition, IIoT transmits a lot of heterogeneous data, which is subject to cyber attacks, and existing classification methods cannot effectively deal with unbalanced data. To solve the above problems, this paper first considers the special network security requirements of the IIoT, and proposes a quantitative evaluation method of network security based on the Analytic Hierarchy Process (AHP). Then, the average under-/oversampling (AUOS) method is proposed to solve the problem of unbalance of network attack data. Finally, an IIoT network security situation assessment classifier based on the eXtreme Gradient Boosting (XGBoost) is constructed. Experiments show that the situation assessment method proposed in this paper can more accurately characterize the network security state of the IIoT. The AUOS method can achieve data balance without generating too much data, and does not burden the training of the model. The classifier constructed in this paper is superior to the traditional classification algorithm.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have