Efficient Intrusion Detection Method Based on Conditional Random Fields

摘要：

With the rapid advancement in the network and communication technologies, intrusion detection becomes a very troublesome problem. An important method for intrusion detection is to model the dynamic behavior of network user based on Hidden Markov Models (HMM), but the HMM model requires strong independence assumptions between the observation sequences of the behaviors of network user, in practice the behaviors of users in networks is dependent So, this motivates us to use Conditional Random Fields (CRFs) to model the behaviors of users because this model has no assumptions on the dependencies among observation sequences.

关键词： Intrusion detection conditional random field hidden markov models

作者: Yunmeng Tan Shengbin Liao Cuitao Zhu

作者单位: Dept. of Electronics and Information Engineering, Huazhong University of Science and Technology, Chi Engineering and Research Center of Information and Technology on Education, Huazhong Normal Universi Dept. of Electronics and Information Engineering, Huazhong South-Center University of Nationalities,

会议类型: 国际会议

会议名称: 2011 International Conference on Computer Science and Network Technology(2011计算机科学与网络技术国际会议 ICCSNT 2011)

会议地点: 哈尔滨

会议语种:英文

页码: 181-184

在线出版日期: 2011-12-24（万方平台首次上网日期，不代表论文的发表时间）