Trust aggregation authentication protocol using machine learning for IoT wireless sensor networks. (May 2021)

• Record Type: Journal Article
• Authors: Chinnaswamy, Santhanakrishnan; K, Annapurani
• Is Part Of: Computers & electrical engineering. Volume 91(2021)
• Publication Date: 2021-05
• Subjects: Authentication -- Trust value -- IoT -- Security -- Machine learning -- Nonrepudiation; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2021.107130
• Languages: English
• ISSNs: 0045-7906

Abstract

Highlights: The trust threshold value is adaptively calculated by applying machine learning technique. Both BT and DT are considered. Based on RQSR computation of the BT value is done. RPSR is used to determine the RREP packet success rate. TAAPML performance is evaluated with respect to PDR, Delay, residual energy and computational overhead of TMM. Abstract: Security is a huge concern in the Internet of Things (IoT)-based Wireless Sensor Networks (WSNs). Authentication becomes critical in a highly secured environment and reliable communication, specifically trustworthiness. In security, nonrepudiation refers to a service, which provides proof of the origin of data and the integrity of the data. Hence, this factor is to be considered in an IoT environment. This work focuses on the proposed Trust Aggregation Authentication Protocol based on the Machine Learning technique (TAAPML). The total trust value is derived for each device from behavior and data trust values by the internet gateways. In the authentication phase, if either the trust value is less than a standard threshold value or the authentication token is invalid, then gateways omit that node. The trust threshold value is adaptively calculated by using a technique called Support Vector Machine (SVM) over the collected traffic data. TAAPML technique performance is evaluated with respect to Packet Delivery Ratio, Delay, Residual Energy, and Computational Overhead. Graphical abstract: Image, graphical abstract