Case Study of Differentially Private in Big Data Publishing

Privacy preserving data publishing is the main concern in current days, because the data being published through internet has been increasing day by day. The big challenge of data distribution is balancing privacy protection and data quality, which are typically considered to be a couple of contradictory factors. It is especially useful for the data owner to publish data, which preserves privacy-sensitive information. The most commonly used privacy protection method is differential privacy (DP) protection. However, the use of DP algorithm is not easy for non-professionals. In this research work, several examples of DP were presented by using Laplace mechanisms (LM), and exponential mechanisms (EM). The rule is created by analyzing data sets based on the calculation of support and differential privacy confidence. All experiment done using python language.