Design and Verification of Hybrid model for Big Data Privacy-Preserving in D2D Communication Environment

Abstract

Nowadays, a massive amount of datasets are being produced by numerous organizations which include but are not limited to private or governmental hospitals, educational institutions, the corporate world, and retail companies all around the world. There have been developed numerous methods in previous years for privacy preservation of the big datasets in the device-to-device (D2D) scenario. Nevertheless, such existing methods have diverse limitations in the modern world related to the secrecy and privacy of the big datasets because the datasets are increasing constantly and existing systems facing challenges in handling the gigantic amount of datasets on daily basis from hackers. In this article, the authors proposed a novel design and verification of a hybrid model for big data privacy-preserving in a D2D communication environment. The outcome of the suggested model demonstrates that the overall execution time and accuracy of this novel model are higher in comparison to the existing models. Further, our model is more robust against diverse assaults from hacker sides for securing the datasets and maintaining secrecy in the desired manner. Our proposed model offers accuracy values on selected datasets i.e. 500, 2000, 4000, 6000, 8000, and 10000, 92%, 92.5%, 93%, 96.5%, 97%, and 99.1%, respectively. In the future, this model can be updated according to diverse application and systems requirements for datasets privacy preserving more accurately for big data in a device to device communication environments.