Differential privacy (DP) gives a rigorous framework for data privacy by giving guarantees on the information leakage for individual data points from the output of an algorithm. However, DP has a somewhat paranoid view of the world which might be too demanding for certain applications.
In this talk, we shall first look at some relaxations of DP - in particular R\'enyi differential privacy (RDP). One of the strengths of RDP is that it preserves the composition properties of DP, i.e. it is easy to bound the privacy loss of a sequence of RDP mechanisms.
Then, we will do a quick overview of local differential privacy (LDP) - a notion of privacy useful for distributed applications. Time permitting, we will also see how differential privacy is related to generalization.
