RETRACTED ARTICLE: Machine Learning Technique to Detect Sybil Attack on IoT Based Sensor Network
Abolfazl Mehbodniya, Julian Webber, Mohammad Shabaz, Hamidreza Mohafez, Kusum Yadav
Abstract
Internet of Things (IoT) devices is getting more and more usage rate day by day with the developments in wireless sensor networks. The heterogeneous network formed by the interconnection of all IoT devices is highly vulnerable to external attacks. Many routing protocol attacks have been put forward, and the attacks continue to increase and diversify daily. However, the proposed detection and prevention methods need to be improved and updated according to today's conditions. False identity attacks are included in the IoT network layer routing protocol (Routing Protocol for Low-Power and Lossy Network, RPL). In the type of fake identity attacks, intrusion detection based on the signal strength of the nodes is one of the most widely used and recommended methods. In resource constrained IoT devices, energy conservation and low processing load are among the most critical issues. Especially, classical methods used in attack detection may be insufficient in detecting and preventing attacks. This study proposes the packet delivery rates of nodes and the detection of fake identity attacks with machine learning approaches such as Naïve Bayes, Random Forest, and Logistic Regression. Simulated identity attacks were detected with a higher success rate (92.14% accuracy) than classical methods.