Intrusion Detection Classification Model on an Improved k-Dependence Bayesian Network

Abstract

Edge computing extends traditional cloud services to the edge of the network, and the highly dynamic and heterogeneous environment at the edge of the network makes the network security situation facing severe challenges. Therefore, it is of great theoretical and practical significance to study and build a high-precision Intrusion Detection Classification Model (IDCM) for network security in the emerging edge computing mode. This paper studies an improved k-dependency Bayesian network (KDBN) structural model that can accurately describe the dependence relationships among system variables and reduce the complexity of the Bayesian network structure by reducing the directed edges of weak dependence. On this basis, this paper constructs an IDCM based on improved KDBN by introducing the maximum a posterior criterion and a virtual augmentation method for samples of small category. The experiments use the KDDCup99 (10%) intrusion detection data set for verification, which show that the IDCM based on improved KDBN has high efficiency, high detection accuracy and high stability, which optimally addresses the issues discussed in many references, such as low detection accuracy and poor stability, for small categories (U2R and R2L) in the KDDCup99 (10%) intrusion detection data set.