GHSOM Cloud Intrusion Detection Method Based on Random Forest and Particle Swarm Optimization Algorithm
Journal of Research in Science and Engineering · 2022
Facing the network security problems in cloud environment and the attack of massive high-dimensional data in the network, eliminate redundant features for feature screening, and using neural network algorithms to detect and prevent network attacks has become one of the important issues faced by information and science and technology today.This paper proposes a GHSOM cloud intrusion detection method combining random forest and particle swarm optimization algorithm.This method uses the characteristics of random forest training fast and can process high-dimensional data to feature processing of data.At the same time, the feature selection results are used as the input data of the subsequent algorithm.The parameters of the traditional GHSOM algorithm in the training process are random, so it will affect the accuracy of the training results.Aiming at this problem, the PSO algorithm is used to improve GHSOM, which improves the efficiency and accuracy of intrusion detection. The comparison experiment of intrusion detection algorithms on the CICIDS2017 data set shows that the intrusion detection algorithm in this paper has a higher detection rate for attacks.