一种新的云计算混合入侵检测算法  

Research on a New Hybrid Intrusion Detection Algorithm for Cloud Computing

作　　者：路亚[1] LU Ya(Artificial Intelligence and Big Data College,Chongqing College of Electronic Engineering,Chongqing 401331,China)

机构地区：[1]重庆电子工程职业学院人工智能与大数据学院,重庆401331

出　　处：《重庆理工大学学报（自然科学）》2020年第10期153-159,共7页Journal of Chongqing University of Technology：Natural Science

基　　金：重庆市重点产业共性关键技术创新专项重点研发项目(cstc2017zdcy-zdyfx0017);重庆市教委科学技术研究项目(自然科学类)(KJ132207)。

摘　　要：提出一种基于网络的混合入侵检测算法,以高精度对云计算系统中内部和外部入侵进行检测。该方法将基于签名的检测技术和基于异常行为的检测技术组合起来以提高检测效率。基于snort的签名入侵检测已知操作的攻击;基于LVQ的异常入侵检测,对异常部分使用聚类;使用分类算法得到异常检测结果。实验结果表明:所提算法攻击检测召回率、检测准确率和F值高于其他方法,误报率低于其他方法,说明本文方法的可行性与有效性。Aiming at the accuracy of intrusion detection in cloud computing systems,a network-based hybrid intrusion detection algorithm is proposed to detect internal and external intrusions in cloud computing systems with high precision.This method combines signature-based detection technology and abnormal behavior-based detection technology to improve detection efficiency.Firstly,snortbased signature intrusion detection is used to detect known operations,and then LVQ-based anomaly intrusion detection is used to cluster the anomaly parts.Finally classification algorithm is used to get the anomaly detection results.The experimental results show that compared with the existing methods,the attack detection rate,detection accuracy and F value of the proposed method are higher than other methods,and the false positive rate is lower than other methods,which shows the feasibility and effectiveness of the proposed method.

关 键 词：云计算 基于签名的检测 基于异常行为的检测 聚类算法 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]