INFORMATION PRIVACY

Catalog description

This course provides a comprehensive introduction to the fundamental concepts and techniques of differential privacy, a crucial framework for ensuring privacy protection in data analysis and sharing. Students will delve into the mathematical foundations of differential privacy, exploring notions of privacy loss, sensitivity, and noise injection, while gaining a solid understanding of how these concepts apply to a wide range of data-driven scenarios. Through a combination of theoretical lectures and practical hands-on exercises, students will learn how to design differentially private algorithms for tasks such as data aggregation, query answering, and machine learning. PREREQ: CYBER 701 OR ADMISSION TO COMPUTER SCIENCE GRADUATE PROGRAM