Speaker: Sewoong Oh

Title: Data processing inequality for differential privacy and applications


We provide a hypothesis testing interpretation to differential privacy and derive natural forward and reverse data processing inequalities. These inequalities are very useful in deriving tight impossibility results, as demonstrated by the following two applications: composing multiple queries and multi-party computation. The impossibility results hold for arbitrary parameter settings (privacy levels, number of queries, etc) and for both standard and approximate differential privacy settings. Further, these impossibility results cannot be improved upon.