Hands-On Differential Privacy

Many organizations today analyze and share large, sensitive datasets about individuals. Whether these datasets cover healthcare details, financial records, or exam scores, it’s become more difficult for organizations to protect an individual’s information through deidentification, anonymization, and other traditional statistical disclosure limitation techniques. This practical book explains how differential privacy (DP) can help.

Authors Ethan Cowan, Michael Shoemate, and Mayana Pereira explain how these techniques enable data scientists, researchers, and programmers to run statistical analyses that hide the contribution of any single individual. You’ll dive into basic DP concepts and understand how to use open source tools to create differentially private statistics, explore how to assess the utility/privacy trade-offs, and learn how to integrate differential privacy into workflows.

With this book, you’ll learn:

• How DP guarantees privacy when other data anonymization methods don’t
• What preserving individual privacy in a dataset entails
• How to apply DP in several real-world scenarios and datasets
• Potential privacy attack methods, including what it means to perform a reidentification attack
• How to use the OpenDP library in privacy-preserving data releases
• How to interpret guarantees provided by specific DP data releases

Table of Contents

Part I. Differential Privacy Concepts

Chapter 1. Welcome to Differential Privacy

Chapter 2. Differential Privacy Fundamentals

Chapter 3. Stable Transformations

Chapter 4. Private Mechanisms

Chapter 5. Definitions of Privacy

Chapter 6. Fearless Combinators

Part II. Differential Privacy in Practice

Chapter 7. Eyes on the Privacy Unit

Chapter 8. Differentially Private Statistical Modeling

Chapter 9. Differentially Private Machine Learning

Chapter 10. Differentially Private Synthetic Data

Part Ill. Deploying Differential Privacy

Chapter 11. Protecting Your Data Against Privacy Attacks

Chapter 12. Defining Privacy Loss Parameters of a Data Release

Chapter 13. Planning Your First DP Project

About the Authors

Mayana Pereira works on applying machine learning and privacy-preserving techniques to a diverse range of practical problems at Microsoft’s AI for Good Team. Mayana is also an active collaborator of OpenDP, an open-source project for the differential privacy community to develop general-purpose, vetted, usable, and scalable tools for differential privacy.

Michael Shoemate works for the research organization TwoRavens, developing tools for visualizing data and conducting statistical analysis. His work has been spread over several different projects: the core project, metadata service, and EventData. He’s also built a collection of reusable modular UI components he’s named ‘common’ for rapid and homogenous frontend development in Mithril.

Ethan Cowan works on software and research topics as part of the Open Differential Privacy (OpenDP) team at Harvard. In particular, he focuses on privatizing machine learning models and developing platforms for analyzing sensitive data with built-in differential privacy. Ethan also works at the intersection of ethics, fairness, and federated learning.