Trust-based support vector regressive (TSVR) security mechanism to identify malicious nodes in the Internet of Battlefield Things (IoBT)

The Internet of Things is an advanced and prominent wireless technology that enables our daily lives easier and more comfortable. The same way it is getting more attention in the military environment and the result of the application is Internet of Battle Field Things (IoBT). IoBT offers many advantages to the battle field environment and at the same time it is getting attention from a security perspective. The battle field things are affected by various attacks because of their significant nature among black hole attack is one of the considerable attacks that affects the IoBT environment more seriously. It is caused by lack of authentication. The battle field things are communicating with other battlefield things without any prior interactions and communications. This blindness leads to security violations. To overcome these issues, in this paper Trust based Support Vector Regression has been proposed. The aim is to detect and eliminate black hole attacks by the way authentication can be ensured. The proposed method makes use of multiple trust metrics to evaluate the trustworthiness of particular IoBT things. Besides, the machine learning algorithm, called Support Vector Regression, is used to classify the black hole nodes and also it predicts the future behaviors of the battle field things. The proposed model has been analyzed in terms of simulation results and this model has been compared with traditional Routing Protocol for Low Power Lossy Network and existing similar model. The proposed model shows prominent results compared with other two models.