Wireless Sensor Networks (WSN) have become increasingly one of the hottest research areas in computer science due to their wide\nrange of applications including critical military and civilian applications. Such applications have created various security threats,\nespecially in unattended environments. To ensure the security and dependability ofWSN services, an Intrusion Detection System\n(IDS) should be in place.This IDS has to be compatible with the characteristics ofWSNs and capable of detecting the largest possible\nnumber of security threats. In this paper a specialized dataset forWSN is developed to help better detect and classify four types of\nDenial of Service (DoS) attacks: Blackhole, Grayhole, Flooding, and Scheduling attacks. This paper considers the use of LEACH\nprotocol which is one of the most popular hierarchical routing protocols in WSNs. A scheme has been defined to collect data\nfrom Network Simulator 2 (NS-2) and then processed to produce 23 features. The collected dataset is called WSN-DS. Artificial\nNeural Network (ANN) has been trained on the dataset to detect and classify different DoS attacks. The results show that WSNDS\nimproved the ability of IDS to achieve higher classification accuracy rate. WEKA toolbox was used with holdout and 10-Fold\nCross Validation methods. The best results were achieved with 10-Fold Cross Validation with one hidden layer. The classification\naccuracies of attacks were 92.8%, 99.4%, 92.2%, 75.6%, and 99.8% for Blackhole, Flooding, Scheduling, and Grayhole attacks, in\naddition to the normal case (without attacks), respectively.
Loading....