基于改进贝叶斯网络的网络安全态势评估

PREDICTION FOR NETWORK SECURITY SITUATION BASED ON IMPROVED BAYESIAN NETWORK

针对现有网络安全态势难以被精确和自主的评估,提出了一种基于改进贝叶斯网络的网络态势评估方法。首先,定义了网络安全态势评估的指标,即网络基础可行性、网络脆弱性和网络威胁性,然后提出了一种改进的贝叶斯网络模型,即动态的贝叶斯网络模型,对网络的结构和推理方法进行了重新定义;在此基础上,通过历史数据来初始化先验概率,通过在线获取的数据来计算后验概率,通过历史数据和监测数据结合来不断修正后验概率。在Matlab环境下进行仿真试验,将所提模型用于对网络安全态势进行预测,并与其他方法进行比较,结果表明所提模型能有效地对网络安全态势进行预测,具有预测精度高的优点,较其他方法具有较大的优越性。

Aiming at the existing prediction model for network security situation are not such accurately and automatically,a network security situation method based on improved Bayesian network is proposed. The indexes for network security situation include network base runnability,vulnerability and threat are defined,then an improved Bayesian network model is proposed,namely,dynamic Bayesian network model,the structure and the reasoning method are re-defined. Furthermore,the posterior probability are rectified by combing historical data and on-line data. In the environment of Matlab,the experiment is operated,the proposed model is used to predict the network security situation,and compared with the other methods. The result shows that the proposed model can predict the network security situation effectively with a relative high prediction accuracy. Therefore,it has a larger priority.