Exploring Differential Privacy in Practice

Every day an unimaginable amount of data is collected from Internet users. All this data is essential for designing, improving and suggesting products and services. In this frenzy of capturing data, privacy is often put at risk. Therefore, there is a need for considering together capturing relevant data and preserving the privacy of each person. Differential Privacy is a method that adds noise in data in a way to keep privacy. Here we investigate Differential Privacy in practice, aiming to understand how to apply it and how it can affect data analysis. We conduct experiments with four classification techniques (including Decision Tree, Naive Bayes, MLP and SVM) by varying privacy degree in order to analyze their accuracy. Our initial results show that low noise guarantees high accuracy; larger data size is not always better in the presence of noise; and noise in the target does not necessary disrupt accuracy.