Intelligent Data Transfer To Ensure Data Privacy In Large Enterprises

Abstract

Enterprises exchange huge volumes of consumer and employee data across several business functions and diversified system landscapes in their day-to-day business. Data is the driving force to make more meaningful and informed decisions and it is the backbone for all kinds of innovations maximizing the profitability of the organizations. With rapid digitization, there is exponential growth in the amount of data collected and exchanged. Hence the paradigm shift had intensified the perplexities of issues around data privacy leading to growing concerns about exchanging data securely. In this paper, a novel model is proposed to handle secure data exchanges intelligently using partial homomorphic encryption with machine learning algorithms such as Linear regression and Bayesian ridge by ensuring the integrity and confidentiality of data fulfilling privacy principles. Later a use case is considered to evaluate the proposed methodology and performance evaluation is carried out between linear regression and Bayes theorem after applying partial homomorphic encryption.