Malicious Code Detection under 5G HetNets Based on a Multi-Objective RBM Model

Abstract

The fifth generation (5G) mobile communication technology brings people a higher perceived rate experience, the high-quality service of high-density user connection, and other commercial applications. As an important means of data processing in 5G heterogeneous networks (HetNets), data fusion technology is faced with a large number of malicious code attacks. Thus, it is particularly important to find an efficient malicious code detection method. However, in the traditional research, due to dataset imbalance, the complexity of the deep learning network model, the use of a single-objective algorithm, and other factors, it brings greater loss and lower detection accuracy. Therefore, how to choose a suitable network model and improve the data classification accuracy in HetNets is a big challenge. To enhance the model's robustness, a multi-objective restricted Boltzmann machine (RBM) model is designed for training. In this article, evaluation indices are used to comprehensively measure the effect of data classification, introducing a strategy pool to improve the effect of data fusion and using non-dominated sorting genetic algorithms (NSGA-II) to deal with the imbalanced malware family. Experimental results demonstrate that the proposed multi-objective RBM model combined with NSGA-II can effectively enhance the data classification accuracy of HetNets and reduce the loss in the process of data fusion.