Intrusion Detection Model Based on Improved Support Vector Machine

• Published in: 2010 Third International Symposium on Intelligent Information Technology and Security Informatics pp. 465 - 469
• Main Authors: Jingbo Yuan, Haixiao Li, Shunli Ding, Limin Cao
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.04.2010
• Subjects: Computer security; Data mining; Data security; hypothesis test theory; Information security; Intrusion detection; Operating systems; support vector machine; Support vector machine classification; Support vector machines; Testing; Training data
• ISBN: 9781424467303; 1424467306
• DOI: 10.1109/IITSI.2010.72

With development and popularization of computer network, network security problems increasingly bring into prominence. Intrusion detection technique can effectively enlarge the scope of protection on network and system. An intrusion detection method based on support vector machine (SVM) is studied. Aiming at the shortcoming of SVM on detecting precision, an intrusion detection model based on improved SVM is put forward according to hypothesis test theory. To confirm the effectiveness of this approach, a simulation testing is done. The experiment results show that the improved SVM has stronger learning ability and higher accuracy and lower false positive rate.