Industrial Internet Security Situation Assessment Method Based on Self-Attention Mechanism

With the promotion of strategies such as “Internet plus”, the deep integration of industrialization and informatization has accelerated, and industrial Internet has become an important support for new economies such as intelligent manufacturing. However, there are numerous high-risk vulnerabilities in industrial control equipment and network systems, facing complex network security threats, leading to increasingly prominent security issues in industrial manufacturing environments. Therefore, industrial Internet security situation assessment and prediction technology has become a research hotspot. This paper proposes an evaluation method based on self attention mechanism to address the issues of model construction and evaluation accuracy. By using self attention mechanism and LSTM neural network to analyze timeseries data, safety situation prediction is generated to improve evaluation accuracy. The experimental results show that the detection accuracy and F1 value of the algorithm proposed in this paper have better performance compared to traditional random forest algorithm, support vector machine, and K-nearest neighbor algorithm.