Differential Privacy in Artificial Intelligence: From, Theory to Practice(NowOpen)

The ebook edition of this title is Open Access and freely available to read online. Differential Privacy in Artificial Intelligence: From Theory to Practice is a comprehensive resource designed to review the principles and applications of differential privacy in a world increasingly driven by data. This book delves into the theoretical underpinnings of differential privacy, its use in machine learning systems, practical implementation details, and its broader social and legal ramifications. Intended as a primer and a deep dive, it lays a solid foundation by introducing essential concepts and mechanisms critical to understanding differential privacy. From theoretical foundations to practical application, the book is organized into five distinct parts. Part I reviews the foundational notions of differential privacy in the central and local models, delving into composition and privacy amplification. The discussion extends to practical strategies for data release and the creation of synthetic data, which is essential for real-world applications. Part II focuses on the application of differential privacy in optimization and learning, examining the integration of privacy measures in machine learning, including private optimization methods and private federated learning. Beyond technical applications, the book highlights the use of differential privacy in critical sectors such as healthcare and energy, and discusses its implications in image and video analysis in Part III. Part IV provides a thorough look at the tools and challenges in deploying privacy-preserving models, including insights into programming frameworks and machine learning tools. Finally, Part V addresses the societal impact of differential privacy, discussing its intersection with public policy, law, fairness, and bias. Targeted at researchers, practitioners, and policymakers; Differential Privacy in Artificial Intelligence: From Theory to Practice aims to be an essential guide for anyone committed to advancing privacy in the digital age, providing the knowledge needed to develop and deploy effective and ethical privacy solutions across various domains.

Table of Contents:
Chapter 1. Overview and Fundamental Techniques Chapter 2. Local Differential Privacy for Privacy-preserving Machine Learning Chapter 3. Composition of Differential Privacy & Privacy Amplification by Subsampling Chapter 4. Data Release and Synthetic Data Chapter 5. Privacy Risks in Machine Learning Chapter 6. Private Optimization Chapter 7. Private Deep Learning Chapter 8. Private Federated Learning Chapter 9. Differential Privacy and Medical Data Analysis Chapter 10. Differential Privacy in Energy Systems Chapter 11. Image and Video Data Analysis Chapter 12. Programming Frameworks for Differential Privacy Chapter 13. Machine Learning Tools Chapter 14. Challenges and Solutions to Deploying Differential Privacy Chapter 15. Testing Private Models Chapter 16. Differential Privacy, Public Policy, and the Law Chapter 17. Relationships between Differential Privacy and Algorithmic Fairness