Differentially Private Data Release: Bias Weight Perturbation Method - A Novel Approach

Abstract

Differential privacy plays the important role to preserve the individual data.  In this research work, discussing a novel approach of releasing private data to the public, which is differentially private, called Bias Weight Perturbation Method. The approach follow here align with principle of differential privacy, it also used concept of statistical distance and statistical sample similarity to quantify the synthetic data generation loss, which is then used to validate our results. Our  proposed approach make use of the deep generative models for providing privacy and it further produce synthetic dataset which can be released to public for further use.