Mobile Ad Hoc Networks has more challenging vulnerabilities compared with wired networks. Mobile ad hoc networking (MANET) has become an important technology in current years because of the rapid proliferation of wireless devices. They are highly vulnerable to attacks due to the open medium, dynamically changing network topology and lack of centralized monitoring point. It is important to search new architecture and mechanisms to protect these networks. Intrusion detection system (IDS) tools are suitable for securing such networks. The main task of IDS is to discover the intrusion from collected data. Some of the features of collected data may be redundant or contribute little to the detection process. So it is essential to select the important features to increase the detection rate. Most of the existing intrusion detection systems detects the intrusion by using large number of data features collected from network. In this work, we propose anomaly based intrusion detection system to detect the malicious activities by collecting statistics from network. Also we use SVM machine learning technique and Rough Set Theory which are used to detect the attacks in an efficient way. Rough set theory preprocesses the feature data to reduce the computational complexity. The support vector machine is trained by using feature set from the Rough set theory for detecting abnormal behavior.

1. John Felix Charles Joseph and Amitabha Das,"Cross-Layer Detection of Sinking Behavior in Wireless Ad Hoc Networks Using SVM and FDA," IEEE transactions on dependable and secure computing, vol. 8, no. 2 march-April 2011.
2. D. K. Srivastava and K. S. Patnaik," Data Classification: A Rough - SVM Approach," Contemporary Engineering Sciences, Vol. 3, 2010, no. 2, 77 – 86.
3. Roman W. Swiniarski and Andrzej Skowron," Rough set methods in feature selection and recognition," Pattern Recognition Letters 24 (2003) 833–849
4. Anazida Zainal and Mohd Aizaini, "Feature Selection Using Rough Set in Intrusion Detection. "IEEE TENCON 2006, 14-17th November 2006, Hongkong.
5. Zbigniew Suraj Chair, "An Introduction to Rough Set Theory and Its Applications," ICENCO'2004, December 27-30, 2004, Cairo, Egypt.
6. Rung-Ching Chen and Kai-Fan Cheng,"Using Rough Set and Support Vector Machine for Network Intrusion Detection, "International Journal of Network Security & Its Applications (IJNSA), Vol 1, No1, April 2009.
7. Rung-Ching Chen and Kai-Fan Cheng,"An Intrusion Detection System of Ad hoc Networks with Multi-attacks Based on Support Vector Machine and Rough Set", Master's Degree Thesis, Chaoyang University of Technology,2009.
8. NS-2 TutorialMultimedia Networking Group,The Department of Computer Science, UVA Jianping Wang. .
9. Shishir K. Shandilya,"A Comprehensive Survey on Intrusion Detection In Manet", International Journal of Information Technology and Knowledge Management July-December 2010, Volume 2.
11. . Sandhya Peddabachigari, "Intrusion Detection Systems Using Decision Trees and Support Vector Machines", Department of Computer Science, Oklahoma State University, USA.
12. Rung-Ching Chen and Kai-Fan Cheng, "An Intrusion Detection System of Ad hoc Networks with Multi-attacks Based on Support Vector Machine and Rough Set", Master's Degree Thesis, Chaoyang University of Technology,2009.
13. Rakesh Shrestha, "A Novel Cross Layer Intrusion Detection System in MANET", 2010 24th IEEE International Conference on Advanced Information Networking and Applications.
14. M. Zhang, "Rough Sets Based Approach to Feature Selection", Department of Computer Science University of Regina, Saskatchewan.
15. Hongmei Deng, Qing-An Zeng and Dharma P,Agrawal "SVM-based Intrusion Detection System for Wireless Ad Hoc Networks", ORB Center for Distributed and Mobile Computig, Department of ECECS, University of Cinncinnati.

Support Vector Machine Rough Set Theory Intrusion Detection System Rosetta