Intrusion detection in mobile AdHoc networks using machine learning approach

Abstract

Mobile ad hoc networking (MANET) has become a key technology in recent years because of the increased usage of wireless devices and their ability to provide temporary and instant wireless networking in situations like flooding and defense. In spite of their attractive applications, MANET poses high security problems compared to conventional wired and wireless networks due to its unique characteristics such as lack of central coordination, dynamic topology, temporary network life and wireless nature of communication. Attack prevention measures, such as the use of encryption and authentication techniques, have been proposed as a first line of defense to reduce the risk of security problems. However such risks cannot be completely eliminated, there is a strong need of intrusion detection systems (IDS) as a second line of defense for securing MANET. Intrusion detection on MANET is a challenging task due to its unique characteristics such as open medium, dynamic topology, lack of centralized management and highly resource constrained nodes. Conventional intrusion detection system developed for wired networks cannot be directly applied to MANET. It needs to be redesigned to suit the ad hoc technology. The proposed system introduces new architecture that uses machine learning approach to maximize the detection accuracy. Proposed IDS architecture uses the combination of Rough Set Theory (RST) and Support Vector Machine (SVM) to make use of the excellent accuracy of SVM and better performance of RST.