2013 · 18 citations · 0 references
ComputingComputer EngineeringComputer ScienceAuthenticationComputer SecurityMachine LearningIntrusion DetectionMobile Network SecurityNetwork AuthenticationThreat DetectionWireless Network SecurityAttack Detection In Mobile NetworksBlackhole Attack DetectionIntrusion Detection In Mobile NetworksMachine Learning For Intrusion DetectionMultilayer PerceptronNeural Network ClassificationNode MobilityPerceptron
MANETs are more susceptible to the security attacks because of the properties such as node mobility, lack of centralized management and limited band width. To reduce the risks of these attacks, various security mechanisms such as encryption and authentication have been proposed. But as we cannot completely eliminate such risks there is a strong need for Intrusion Detection Systems (IDS). So, in this paper we propose a neural network method based on MLP (Multi Layer Perceptron) for detecting normal and attacked behaviour of the system. The method was tested for black hole and gray hole attacks. We have implemented these attacks using NS2 simulator. The method successfully detected these attacks. This paper presents a graphical representation of the results.