摘要
网络安全态势感知NSSA(Network Security Situation Awareness)是目前网络安全领域的热点研究内容,开展NSSA的研究,对提高我国的网络安全水平有着重要的意义。本文提出了一个NSSA模型,利用多层前馈神经网络,对采集的多个异质的传感器数据进行了融合。为提高融合的实时性,本文还设计了简单易行的特征约简方法,大大降低了融合引擎的输入维数。最后,本文利用安全态势生成算法,对网络安全事件进行了加权量化。实验表明,本文所提出的模型和方法是可行的和有效的。
Network Security Situation Awareness （NSSA） is a hot research spot in the area of network security and it is significant to study NSSA in order to improve the security level of our nation. This paper presents a NSSA model based on data fusion. The NSSA model employs multi-layer feedforward neural network as its fusion engine and fuses the data provided by the sensors in an intelligent and efficient manner. Furthermore, this paper discusses a network security situation generation agorithm which expresses the security situation by the weighted quantization of security events. In addition,it also designs a feature reduction method in order to improve the real-time nature of the NSSA. Our model and approach are proved to be feasible and effective through a series experiments using real network traffic.
出处
《计算机科学》
CSCD
北大核心
2008年第8期69-73,共5页
Computer Science
基金
国家“八六三”高技术研究发展计划项目基金(2007AA01Z401)
国防十一五预研重点项目(513150602)
高等学校博士学科点专项科研基金项目(20050217007)
关键词
网络安全态势感知
多层前馈神经网络
多传感器融合
特征约简
安全态势生成
Network security situational awareness, Multi-layer feedforward neural network, Multi-sensor data fusion, Feature reduction,Security situation generation
