How can researchers use sensitive datasets for machine learning and statistics without compromising the privacy of the individuals who contribute their data?  In this talk I will describe my work on the foundations of differential privacy, a rigorous framework for answering this question.  In the past decade, differential privacy has gone from largely theoretical to widely deployed, and a theme of the talk will be how new deployments are forcing us to revisit foundational questions about differential privacy.  This talk will cover a range of issues from the fundamental—like optimal private statistical inference—to the applied—like auditing differentially private machine learning.