Differential Privacy, with roots in cryptography, is a strong mathematical scheme for privacy preserving and is now becoming a standard for private data analysis which has been deployed in both governments and industries. In this class, you will learn the motivation and the developments of differential privacy, with its application to Machine Learning and Statistics, from both theory and practice. We will talk about basic and advanced properties, commonly used mechanisms and techniques of differential privacy. Moreover, we will discuss differential privacy in classification and regression problems, and its behaviors in modern deep learning models.