An Anomaly Detection Model Based on Deep Auto-Encoder and Capsule Graph Convolution via Sparrow Search Algorithm in 6G Internet of Everything

In recent years, driven by the continuous development of mobile Internet technology and artificial intelligence technology, the improvement of the manufacturing level of 6G Internet-of-Everything (IoE) products and the increase in residents’ income level, the 6G IoE industry has shown a sustained and stable development trend. However, 6G IoE has great security risks. Network anomaly detection is very important for 6G IoE. The anomaly detection method based on traditional deep auto-encoder uses the reconstruction error to determine whether the sample to be measured is normal data or abnormal data. However, the reconstruction errors generated by the above method on normal data and abnormal data are very close, which leads to some abnormal data being easily misclassified as normal data. Therefore, an anomaly detection method based on deep auto-encoder and capsule graph convolution via sparrow search algorithm in 6G IoE is proposed. Firstly, the capsule graph network uses the bottleneck feature of the input sample to generate the bottleneck feature of the pseudo-abnormal data, so as to increase the abnormal data information in the training set. The capsule dynamic fusion strategy aggregates different factors to obtain new item embedding. Secondly, deep auto-encoder reconstructs the bottleneck characteristics with abnormal data information into normal data as much as possible, and increases the difference of reconstruction error between abnormal data and normal data. In the process of network classification, we use the sparrow search algorithm to find the optimal value of the function. And at the same time, it prevents the algorithm from prematurity and improves the classification effect. Finally, we conduct experiments on public data sets to compare with other advanced methods. Experimental results show that the proposed method can effectively enlarge the difference between normal data and abnormal data in reconstruction error.