A Machine Learning Approach for Detecting Spoofing Attacks in Wireless Sensor Networks

Abstract

Currently, there is a wide variety of low-cost radio technologies being used to enable wireless communication in some important emerging applications such as smart grids, smart cities and the Internet of Things (IoT). However, easy access to these new radio technologies brings a security problem due to the fact that it is very easy for a malicious user to perform passive wireless signal scanning on these networks and use this information to launch identity-based attacks. In this paper, we propose a new machine learning based strategy to detect spoofing attacks in wireless sensor networks (WSNs). Based on detailed analytical models for the mobile radio channel, the proposed algorithm combines two classifiers to process and analyze the instant samples of received signal strength to detect attacks. The algorithm is optimized for scenarios where the legitimate node and the attacking node are at the same distance or at a very close distance from each other in relation to the landmark, what is the worst case scenario. The results show that the proposed strategy improves the performance of the attack detection in about 10% regarding a similar approach in the literature.