A Case Study on Differential Privacy

Throughout the ages, human beings prefer to keep most things secret and brand this overall state with the title of privacy. Like most significant terms, privacy tends to create controversy regarding the extent of its flexible boundaries, since various technological advancements are slowly leaching away the power people have over their own information. Even as cell phone brands release new upgrades, the ways in which information is communicated has drastically increased, in turn facilitating the techniques in which people’s privacy can be tampered with. Therefore, questioning the methodology by which people can maintain their privacy in the twenty-first century is a validated action undoubtedly conducted by the multitude of the world’s population. Admittedly, data is everywhere. The world has become an explosion of information, and it should not come as a surprise, especially in a time when data storage is cheap and accessible. Various institutions use this data to conduct research, track the behavior of users, recommend products or maintain national security. As a result, corporations’ need for information is growing by the minute. Companies need to know as much as possible about their customers. Nonetheless, how can this be achieved without compromising the privacy of individuals? How can companies provide great features and maintain great privacy? These questions can be answered by a current, anticipated research topic in the field of data privacy: differential privacy. Differential privacy is a branch of statistics that aims to attain the widest range of data while achieving a robust, significant and mathematically accurate definition of privacy. Thus, the objective of this thesis will be describing and analyzing the concept of differential privacy and its properties that lead to the betterment of data privacy. Hence, we will try to study the basic state-of-the-art methods, the model and the challenges of differential privacy. After analyzing the state-of-the-art differential privacy methods, this thesis will focus on an actual case study that is concerned with two types of different datasets which are experimented with one of the methods of differential privacy methods. We design a basic framework that tries to achieves differential privacy guarantee and evaluate the results regarding the level of privacy achieved