Email this article 
Open Access
Subscription or Fee Access
Analysis and Study of Intrusion Detection Systems Using Data Mining Machine Learning Techniques
Abstract
Intrusions pose a serious security problem in the network environment. Security of computer systems is very important to their utility and acceptance. Security in the network environment is maintained by monitoring the data. Security of a network also depends on the amount of data to be monitored. Unfortunately the available amount of network audit data instances is usually large that usually demands human labeling which is a tedious and time consuming task as well as proven to be expensive. To solve similar kinds of problems such as mentioned above, like the human interventions or high level of data biasing intrusion detection systems implement a suite of techniques that use data mining machine learning systems to identify the attacks against computers and network infrastructures. The suites of IDS techniques are widely discussed through out the paper.
Keywords
References
“An Introduction to Intrusion Detection Assessment for System and Network Security Management” For an overview of IDSs and their capabilities, read the white paper at
“Anomaly Based Intrusion Detection Based on the Junction Tree Algorithm “, Journal of Information Assurance and Security 2 (2007) 184-188 Evgeniya Nikolova and Veselina Jecheva Burgas Free University, Faculty for Computer Science and Engineering, 62 Str. San Stefano, 8001 Burgas, Bulgaria.
“Application level intrusion detection using a sequence learning algorithm “, Source Pages: 115 Year of Publication: 2006 ISBN: 978-0-542-74370-2, Order Number: AAI3221685 by yuhong dong florida atlantic university Boca Raton, FL, USA
“Automatically constructing compiler optimization heuristics using supervised learning”, by Cavazos, John
“Comparision of unsupervised anomaly detection methods for syatems health management using space shuttlemain Engine Data” R. A. Martin, M. Schwabacher, N. Oza, and A. Srivastava Intelligent Systems Division NASA Ames Research Center Moffett Field,CA)
”Data Mining for Network Intrusion Detection: How to Get Started,” Eric Bloedorn et al, Technical paper, 2001.
“Data Mining Techniques for (Network) Intrusion Detection Systems”, Theodoros Lappas and Konstantinos PelechrinisDepartment of Computer Science and Engineering UC Riverside, Riverside CA 92521 {tlappas,kpele}@cs.ucr.edu
”Intrusion Detection Systems (IDS) what are they and how do They Work?” By Wayne T Work Security Gauntlet Consulting 56 Applewood Lane Naugatuck, CT 06770 203.217.5004
“Intrusion Detection System”, by Security Gauntlet Consulting 56 Applewood Lane Naugatuck, CT 06770 203.217.5004 by Wayne T Work
” Intrusion Detection Systems”, NIST Special Publication Rebecca Bace3, Peter Mell4
“Intrusion detection system based on growing grid neural network”, Mora, F.J.; Macia, F.; Garcia, J.M.; Ramos, H. Electrotechnical Conference, 2006. MELECON 2006. IEEE Mediterranean Volume , Issue , 16-19 May 2006 Page(s):839 – 842 Digital Object Identifier 10.1109/MELCON.2006.1653229
"Intrusion Detection System to Detect Variant Attacks Using LearningAlgorithms with Automatic Generation of Training Data”, ITCC, Proceedings of the International Conference on Information Technology:Coding and Computing (ITCC'05) - Volume I Volume 01, Pages: 650 - 655 Year of Publication: 2005 ISBN:0-7695-2315-3 by akina yamada, yukta miyake, kiesuke takemor, Toshiaki Tanaka KDDI R&D Laboratories INC, Japan IEEE Computer Society Washington, DC, USA
“Learning program behavior profiles for intrusion detection”, Ghosh, A. K., A. Schwartzbard, and M. SchatzIn Proc. 1st USENIX, 9-12 April,1999
“Learning intrusion detection: supervised or unsupervised?”, Pavel Laskov, Patrick D¨ussel, Christin Sch¨afer and Konrad RieckFraunhofer-FIRST.IDA, Kekul´estr. 7, 12489 Berlin, Germany {laskov, duessel, christin, rieck}@first.fhg.de
“Multi-Level Intrusion Detection System (ML-IDS)“, Al-Nashif, Y.;Kumar, A.A.; Hariri, S.; Guangzhi Qu; Yi Luo; Szidarovsky, F.Autonomic Computing, 2008. ICAC apos;08. International Conference on Volume, Issue, 2-6 June 2008 Page(s): 131 – 140 Digital Object Identifier 10.1109/ICAC.2008.25
”The KDD process for extracting useful knowledge from volumes of data,” Fayyad, U. M., G. Piatetsky-Shapiro, and P. Smyth,Communications of the ACM 39 (11), November 1996, 2734.
“Unsupervised anomaly detection in network intrusion detection using clusters “, ACM International Conference Proceeding Series; Vol. 102 Proceedings of the Twenty-eighth Australasian conference on Computer Science - Volume 38 Newcastle, Australia Pages: 333 - 342 Year of Publication: 2005 ISBN ~ ISSN: 1445-1336, 1-920-68220-1
”Unsupervised Intrusion Detection System”, by Aykut ¨Oks uz, Technical University of Denmark Informatics and Mathematical Modelling Building 321, DK-2800 Kongens Lyngby, Denmark www.imm.dtu.dk Kongens Lyngby 2007 IMM-M.Sc.-2007-20
“Unsupervised Anomaly Detection in Network Intrusion Detection Using Clusters” Kingsly Leung Christopher Leckie y yNICTA Victoria Laboratory Department of Computer Science and Software Engineering The University of Melbourne Parkville, Victoria 3010 Australia Email:caleckie@cs.mu.oz.au
“ Unsupervised Anomaly Detection In Network Intrusion Detection Using Clusters “, Proceedings of National Conference on Challenges &Opportunities in Information Technology (COIT-2007) RIMT-IET,Mandi Gobindgarh. March 23, 2007 Satinder Singh1, Guljeet Kaur Computer Science Department, Lyallpur Khalsa College, Jalandhar
“Using Unsupervised Learning for Network Alert Correlation “, Reuben Smith1, Nathalie Japkowicz1, Maxwell Dondo2 and Peter Mason2 school of information Technology and Engineering (SITE), Univeersity of Ottava ON Canada, Defence Research and Development Canada (DRDC) Ottava ON Canada.
Unsupervised Anomaly Detection with Unlabeled Data Using Clustering, Witcha Chimphlee, Prof.Dr.Abdul Hanan Abdullah, Associate Prof Dr.Mohd Noor Md Sap Faculty of Computer Science and Information Systems University Technology of Malaysia, Proceedings of the Postgraduate Annual Research Seminar 2005
Refbacks
- There are currently no refbacks.
This work is licensed under a Creative Commons Attribution 3.0 License.