Network Situation Assessment Method for Industrial Internet of Things

Industrial internet of things is facing the increasingly serious threat of network attacks, but the traditional situation assessment methods are not suitable for industrial internet of things, and the existing network attack classification methods cannot accurately evaluate with a small number of sample data. In view of the above problems, this paper proposes a network situation assessment method based on attack classification according to the characteristics of industrial internet of things. This method utilizes the One-Sided Selection algorithm (OSS) and Generative Adversarial Networks (GAN) to handle imbalanced datasets, and employs the MultiAttention-BiLSTM-DNN (MABD) model to achieve network attack classification, ultimately obtaining the situation value. With the traditional situation assessment method based on attack classification, the experiment results show that the proposed assessment method has better evaluation effect.