Improving one-class SVM for anomaly detection

by: Kun-Lun Li, Hou-Kuan Huang, Sheng-Feng Tian, Wei Xu

International Conference on Machine Learning and Cybernetics, 2003 International Conference on, Vol. 5 (2003), pp. 3077-3081 Vol.5.

View FullText article

IEEE Explore

Reviews [Write a review of this article]

There are no reviews of this article

Find related articles from these CiteULike users

sdvillal, PeterRabbit, fabiomanzoni

Find related articles with these CiteULike tags

classification, classifier, error-prediction, kernel, machine-learning, occ, occ-support-vector, one-class, outlier-detection, quantile-estimation, support-vector-machine, svm

Abstract

With the tremendous growth of the Internet, information system security has become an issue of serious global concern due to the rapid connection and accessibility. Developing effective methods for intrusion detection, therefore, is an urgent task for assuring computer & information system security. Since most attacks and misuses can be recognized through the examination of system audit log files and pattern analysis therein, an approach for intrusion detection can be built on them. First we have made deep analysis on attacks and misuses patterns in log files; and then proposed an approach using support vector machines for anomaly detection. It is a one-class SVM based approach, trained with abstracted user audit logs data from 1999 DARPA.

@inproceedings{citeulike:1109643, abstract = {With the tremendous growth of the Internet, information system security has become an issue of serious global concern due to the rapid connection and accessibility. Developing effective methods for intrusion detection, therefore, is an urgent task for assuring computer \& information system security. Since most attacks and misuses can be recognized through the examination of system audit log files and pattern analysis therein, an approach for intrusion detection can be built on them. First we have made deep analysis on attacks and misuses patterns in log files; and then proposed an approach using support vector machines for anomaly detection. It is a one-class SVM based approach, trained with abstracted user audit logs data from 1999 DARPA.}, author = {Li, Kun-Lun and Huang, Hou-Kuan and Tian, Sheng-Feng and Xu, Wei }, booktitle = {International Conference on Machine Learning and Cybernetics}, citeulike-article-id = {1109643}, journal = {International Conference on Machine Learning and Cybernetics, 2003 International Conference on}, keywords = {occ-support-vector}, pages = {3077--3081 Vol.5}, posted-at = {2007-02-16 11:29:31}, priority = {2}, title = {Improving one-class SVM for anomaly detection}, url = {http://ieeexplore.ieee.org/xpls/abs\_all.jsp?arnumber=1260106}, volume = {5}, year = {2003} }

RIS record

TY - CONF ID - citeulike:1109643 L3 - citeulike-article-id:1109643 TI - Improving one-class SVM for anomaly detection T2 - International Conference on Machine Learning and Cybernetics JF - International Conference on Machine Learning and Cybernetics, 2003 International Conference on VL - 5 SP - 3077 EP - 3081 Vol.5 N2 - With the tremendous growth of the Internet, information system security has become an issue of serious global concern due to the rapid connection and accessibility. Developing effective methods for intrusion detection, therefore, is an urgent task for assuring computer & information system security. Since most attacks and misuses can be recognized through the examination of system audit log files and pattern analysis therein, an approach for intrusion detection can be built on them. First we have made deep analysis on attacks and misuses patterns in log files; and then proposed an approach using support vector machines for anomaly detection. It is a one-class SVM based approach, trained with abstracted user audit logs data from 1999 DARPA. KW - occ-support-vector AU - Li, Kun-Lun AU - Huang, Hou-Kuan AU - Tian, Sheng-Feng AU - Xu, Wei PY - 2003/// UR - http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1260106 ER -

RIS BibTeX