Data-Mining Techniques for Routing Attacks in Wireless Sensor Networks

Abstract

As the Wireless sensor networks are getting complex, with the increasing deployment of wirelesssensor devices and networks, security becomes a critical challenge for sensor networks. In this work, a technique is proposed to detect anomaly nodes in WSN using association with rules and applying clustering algorithm to improve routing in wireless sensor networks. The scheme uses the ANN algorithm to extract traffic patterns from both routing table and network traffic packets and subsequently the K-means cluster algorithm adaptively generates a detection model. Through the combination of these two algorithms, routing attacks can be detected effectively and automatically. The proposed work has improved to detect the attacks which were not identified with the other methods. The detection scheme proposed works with no priori knowledge and is efficient to identify routing attacks in various different wireless sensor networks.