Paper Title :SVM Based Determining Attackers And Localizing Adversaries In Wireless Net Works
Author :S.Velmurugan, N.Praveen
Article Citation :S.Velmurugan ,N.Praveen ,
(2014 ) " SVM Based Determining Attackers And Localizing Adversaries In Wireless Net Works " ,
International Journal of Advance Computational Engineering and Networking (IJACEN) ,
pp. 99-103,
Volume-2,Issue-4
Abstract : Abstract- Wireless spoofing attacks are easy to launch and can significantly impact the performance of networks. All
though the Identity of a node can be verified through cryptographic authenticate, conventional security approaches are not
always desirable because of their overhead requirements. In propose to use spatial information, a physical property associate
with each node, hard to falsify, and not reliant on cryptographic the basis for 1) detecting spoofing attacks; 2) determining
the number of attackers when multiple adversaries masquerading as the same node identity; and 3) localizing multiple
adversaries. In propose to use the spatial correlation of received signal strength (RSS) inherited from wireless nodes to detect
the spoofing attacks. Then formulate the problem of determining the number of attackers as a multiclass detection problem.
Cluster based mechanism is developed to determine the number of attackers. When the training data are available, to
explore using the Support Vector Machines (SVM) methods to further improve the accuracy of determining the number of
attackers. In addition, to developed an integrated detection and localization system that can localize the positions of multiple
attackers. The evaluated our techniques through two tested using both an 802.11 (Wi-Fi) network and an 802.15.4 (Zig-
Bee) network in two real office buildings. Our experiment results show that our proposed methods can achieve over 90
percent Hit Rate and Precision when determining the number of attackers. Our localization results using a representative set
of algorithms provide strong evidence of high accuracy of localizing multiple adversaries. The existing techniques are used
to detect attackers but don’t know how it attacks. In this paper, we extend the RSS techniques to find out how attackers will
attack by monitoring the attacker’s activities.
Type : Research paper
Published : Volume-2,Issue-4
DOIONLINE NO - IJACEN-IRAJ-DOIONLINE-609
View Here
Copyright: © Institute of Research and Journals
|
|
| |
|
PDF |
| |
Viewed - 39 |
| |
Published on 2014-04-15 |
|