A Weighted-Dissimilarity-Based Anomaly Detection
International Conference on Convergence and Hybrid Information Technology 2009
A Weighted-Dissimilarity-Based Anomaly Detection
Method for Mobile Networks
hj7989
ABSTRACT
School of computer and Information Comm. Eng Catholic University of Daegu Gyeongsan, Gyeongbuk 712-702, Republic of Korea +82-53-850-2742
Hwa-Ju Lee
School of computer and Information Comm. Eng Catholic University of Daegu Gyeongsan, Gyeongbuk 712-702, Republic of Korea +82-53-850-2742
Kyung-Sook Lee
lks8682
School of computer and Information Comm. Eng Catholic University of Daegu Gyeongsan, Gyeongbuk 712-702, Republic of Korea +82-53-850-2742
Ihn-Han Bae
Mobile wireless networks continue to be plagued by theft of identity and intrusion. Both problems can be addressed in two different ways, either by misuse detection or anomaly-based detection. In this paper, we propose a weighted-dissimilarity-based anomaly detection method that can effectively identify abnormal behavior such as mobility patterns of mobile wireless networks. In the proposed algorithm, a normal profile is constructed from normal mobility patterns of mobile nodes in mobile wireless networks. From the constructed normal profile, the dissimilarity is computed by a weighted dissimilarity measure. If the computed dissimilarity value is greater than the dissimilarity threshold that is a system parameter, an alert message is occurred. The performance of the proposed method is evaluated through a simulation. From the result of the simulation, we know that the proposed method is superior to the performance of anomaly detection methods using other dissimilarity measures.
Cellular-based wireless networks have become very popular as more and more users not only communicate with others using cellular phones but also perform important and sensitive tasks such as E-Shopping and E-Banking. The booming new services, while bringing great convenience, have caused serious security concerns. Although there are many authentication protocols in cellular mobile network, how to design a highly secure cellular mobile network is still a very challenging issue due to the open radio transmission environment and the physical vulnerability of mobile devices [2].
In general, two complementary approaches exist to protect a system: prevention and detection. Intrusion prevention technique, such as encryption and authentication, can deter attackers from malicious behavior. The history of security research has showed that prevention based techniques alone can only reduce the intrusions rather than totally eliminate them. No matter how many intrusion prevention measures are deployed, sooner or later, an attacker can exploit some security holes to break into a system. Therefore, intrusion detection systems served as the second line of defense, are indispensable for a reliable system [3].
In this paper, we propose a weighted-dissimilarity-based anomaly detection method that can effectively identify abnormal behavior such as mobility patterns of mobile wireless networks. In the proposed algorithm, a normal profile is constructed from normal mobility patterns of mobile nodes in mobile wireless networks. From the constructed normal profile, the dissimilarity is computed by a weighted dissimilarity measure. When an intrusion occurs, the attacker masquerading the legitimate user trends to have a different used pattern. Therefore, we can detect anomaly by comparing the used patterns. If the value of the weighted dissimilarity measure of a user activity is greater than the dissimilarity threshold that is a system parameter, an alert message is occurred. Otherwise, the activity is identified normal behavior. The rest of this paper is organized as follows. Section 2 gives a brief description of related works for intrusion detection techniques in wireless networks. Section 3 describes similarity and dissimilarity measures that are used to detect abnormal mobility patterns. Section 4 proposes a dissimilarity-based anomaly detection model for mobile wireless networks. Section 5 presents the simulation study of our proposed method. In Section 6, we conclude this paper and point out future work.
Keywords
Mobile wireless networks, Anomaly detection, Dissimilarity
1. INTRODUCTION
The nature of mobile computing environment makes it very vulnerable to an adversary’s malicious attacks. The use of wireless links renders the network susceptible to attacks ranging from passive eavesdropping to active interfering. Unlike wired networks where an adversary must gain physical access to the network wires or pass through several lines of defenses at firewalls and gateways, attacks on a wireless network can come from all directions and target at any node. Damages can include leaking secret information, message contamination, and node impersonation [1].
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. ICHIT’09, August 27–29, 2009, Daejeon, Korea.
The Anomaly Detection ... 1人阅读 7页 2.00 Anomaly Detection with.... Network-Based H∞ Filt... 13人阅读 5页 2.00 Effects of real-...
Topic detection based on... 暂无评价 7页 免费 A Weighted-Dissimilarity..... Benchmarking anomaly-bas... 暂无评价 8页 免费 An Anomaly Intrusion Det.....
A Weighted-Dissimilarity... 6页 10财富值 Evidence-based Anomaly D... ... Rule-based Anomaly Pattern Detection for Detecting Disease Outbreaks This ...
Key Challenges – Detecting collective anomalies – Data sets are very large Anomaly Taxonomy* Anomaly Detection Point Anomaly Detection Classification Based ...
Network-based anomaly intrusion detection with numeric-and-nominal mixed data_专业资料。维普资讯 http://www.cqvip.com JunlfSaga nvri(nlhEio)20,05:140ora...
Anomaly Detection : A Survey VARUN CHANDOLA University of Minnesota ARINDAM BANERJEE University of Minnesota and VIPIN KUMAR University of Minnesota Anomaly ...
Vehicle Detection Meth... 14人阅读 5页 2.00 Learning Vector Quanti... 2人阅读 4页 2.00 Network-based anomaly ... 1人阅读 6页 2....
Anomaly Detection System Based on Principal Component Analysis and Support Vector Machine_专业资料。维普资讯 http://www.cqvip.com e ● ’ 维普资讯 http:...
? Types of anomaly detection schemes – Graphical & Statistical-based – Distance-based – Model-based ? Tan,Steinbach, Kumar Introduction to Data Mining...
Behavior Clustering for Anomaly Detection_专业资料。REERHPPRSAC AE 雾≯ 霉慧... Anomaly detection meth... 4人阅读 5页 2.00 Network-based anomaly ....
热门文档