Title :
An online unsupervised intrusion detection system based-on SVM
Author :
Liang, Hu ; Nurbol ; Lin, Lin ; Kuo, Zhao
Author_Institution :
Dept. of Comput. Sci. & Technol., Jilin Univ., Changchun, China
Abstract :
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.
Keywords :
data mining; pattern classification; security of data; support vector machines; SVM classifier; SVM training set; frequency weighted mining; online unsupervised intrusion detection system; real-time data processing; support vector machine; system call frequency value; vector set; Clustering algorithms; Computer networks; Computer security; Data models; Data security; Frequency; Intrusion detection; Machine learning; Support vector machine classification; Support vector machines; Support Vector Machine; frequency weighted; intrusion detection; linear scanning;
Conference_Titel :
Broadband Network & Multimedia Technology, 2009. IC-BNMT '09. 2nd IEEE International Conference on
Conference_Location :
Beijing
Print_ISBN :
978-1-4244-4590-5
Electronic_ISBN :
978-1-4244-4591-2
DOI :
10.1109/ICBNMT.2009.5348531
