A Lightweight Anomaly Detection System for Black Hole Attack

Abstract

Mobile ad hoc networks (MANETs) are now key in today’s new world. They are critically needed in many situations when it is crucial to form a network on the fly while not having the luxury of time or resources to configure devices, build infrastructure, or even have human interventions. Ad hoc networks have many applications. For instance, they can be used in battlefields, education, rescue missions, and many other applications. Such networks are characterized by high mobility, low resources of power, storage, and processing. They are infrastructure-less; this means that they don’t use infrastructure equipment for communication. These networks rely instead on each other for routing and communication. MANETs use a hopping mechanism where each node in a network finds another node within its communication range and use it as a hop for delivering the message through another node and so on. In standard networks, there is dedicated equipment for specific functions such as routers, servers, firewalls, etc., while in ad hoc networks, every node performs multiple functions. For example, the routing function is performed by nodes. Hence, they are more vulnerable to attacks than standard networks. The main goal of this paper is to propose a solution for detecting black hole attacks using anomaly detection based on a support vector machine (SVM). This detection system aims at analyzing the traffic of the network and identifying anomalies by checking node behaviors. In the case of black hole attacks, the attacking nodes have some behavioral characteristics that are different from normal nodes. These characteristics can be effectively detected using our lightweight detection system. To experiment with the effectiveness of this solution, an OMNET++ simulator is used to generate traffic under a black hole attack. The traffic is then classified into malicious and non-malicious based on which the malicious node is identified. The results of the proposed solution showed very high accuracy in detecting black hole attacks.