基于协同神经网络的云通信异常检测方法  

The Network Traffic Anomaly Detection Method Based on Synergetic Neural Networks in Cloud Communications

作　　者：石云[1,2,3] 陈钟[2,3] 

机构地区：[1]六盘水师范学院计算机科学与信息技术系,贵州六盘水553001 [2]北京大学信息科学技术学院,北京100871 [3]北京大学网络与软件安全保障教育部重点实验室,北京100871

出　　处：《六盘水师范学院学报》2014年第4期63-67,共5页Journal of Liupanshui Normal University

基　　金：国家自然科学基金(61170263)

摘　　要：云计算和服务的全分布式和开放结构成为潜在入侵者一个更具吸引力的目标,安全是云计算最大的挑战。为了减少安全隐患,提出了基于协同神经网络网络流量动态特性的云通信网络流量异常检测方法,用协同动力学方程与一组序参量来描述云通信网络通信系统的复杂行为,当这个方程式演变时,只有主要因素决定的序参量可以收敛到1,从而检测出异常。文中使用标准的美国国防部高级研究计划局的数据集进行方法性能的评估,实验结果表明,该方法能有效地检测出网络流量异常,并达到较高的检测率和低误报率。The fully distributed and open structure of cloud computing and services have become an even more attractive target for potential intruders. Security is the greatest challenge of cloud computing. To reduce security risks, the approaches of the network traffic anomaly detection in cloud communications have been presented, which analyze dynamic characteristics of the network traffic based on the synergetic neural net-works. A synergetic dynamic equation with a group of the order parameters is used to describe the complex behaviors of the network traffic system in cloud communications. When this equation is evolved, only the or-der parameter determined by the primary factors can converge to 1. Then, the anomaly can be detected. The paper evaluate the performance of this approaches using the standard Defense Advanced Research Projects Agency data sets. Experimental results show that the approaches can effectively detect the network traffic anomaly and achieve the high detection probability and the low false alarms rate.

关 键 词：异常检测 云通信 网络流量 协同神经网络 云安全 

分 类 号：TP309[自动化与计算机技术—计算机系统结构]