AN ONLINE UNSUPERVISED INTRUSION DETECTION SYSTEM BASED-ON SVM

摘要：

Using frequency weighted mining algorithm with real-time data processing capability to calculate each system call’s frequency value for existed audit records, and we got a vector set of progress. The vector set was linearly scanned and its progresses were labeled as “normal or “attack according to their distance relations. Then we got a SVM training set without man-made supervision. Finally, the normal behavior profiles for monitoring the target system were generated by SVM classifier so as to build a practical online intrusion detection system without human intervention.

关键词： intrusion detection frequency weighted linear scanning Support Vector Machine

作者: Hu Liang Nurbol Lin Lin Zhao Kuo

作者单位: Department of Computer Science and Technology,Jilin University, Changchun

会议类型: 国际会议

会议名称: 2009 2nd IEEE International Conference on Broadband Network & Multimedia Technology(2009年宽带网络与多媒体国际会议 IEEE IC-BNMT2009)

会议地点: 北京

会议语种:英文

页码: 438-442

在线出版日期: 2009-10-18（万方平台首次上网日期，不代表论文的发表时间）