A Network Security Situation Prediction for Consumer Data in the Internet of Things Using Variational Mode Decomposition (VMD) and Fused CNN-BiLSTM-Attention

Aimin Yang, Baoshan Xie, Yikai Liu, Liya Wang, Jie Li

Abstract: Consumer data in e-commerce platforms relies heavily on Internet of Things (IoT) devices, which bring forth numerous security threats. As an emerging proactive defense technology, IoT network security situation prediction has the capability to forecast the overall future network security conditions. However, the original network security situation sequences exhibit nonlinear and unstable characteristics, which diminish the direct predictive accuracy. In this paper, we propose a prediction model based on decomposition-fusion. Specifically, we propose a novel approach to compute situation values by integrating three key factors: IoT attack factors, IoT attack probabilities, and IoT threat factors. Then, we decompose the original sequence into more stable subsequences using Variational Mode Decomposition (VMD), and construct a Convolutional Neural Network (CNN)-Bidirectional Long Short-Term Memory (BiLSTM)-Attention architecture to predict these subsequences. Finally, we utilize BiLSTM to fuse the results from each subsequence calculation, generating the ultimate prediction. Experimental results underscore the significant advantages of this method in terms of stability and forecasting precision, with a fitting degree of 0.99. This method provides a more comprehensive security defense system for e-commerce platforms and IoT applications, thereby enhancing the overall security of consumer data. Furthermore, it presents a novel solution for the field of network security.