Antonella Basso and Kyla Finlayson
Abstract
With the rise of technology and data, privacy has become increasingly important to both companies and individuals. Although big data has helped to bring about numerous breakthroughs within the healthcare industry, much of the data that both researchers and organizations use to train their models contain sensitive information about individuals. Differential privacy is a solution—it enables us to publicly share important data without revealing information that could identify particular subjects and hence violate their right to privacy.
In this work, we introduce the topic of differential privacy—what it is, why it’s useful, and how we can implement it in both R and Python.
Visit Website
Github Repo