Chalmers University of Technology, Sweden
Title: Getting Personal with Differential Privacy
Differential privacy has recently grabbed the attention of many privacy researchers. It provides a way to get useful information about sensitive data without revealing much about any one individual. It enjoys many nice compositionality properties not shared by other approaches to privacy, including, in particular, robustness against side-knowledge.
Designing differentially private mechanisms from scratch can be a challenging task. One way to make it easier to construct new differential private mechanisms is to design a system which allows more complex mechanisms (programs) to be built from differentially private building blocks in principled way, so that the resulting programs are guaranteed to be differentially private by construction. In this talk I will review the basic ideas of differential privacy and describe a new accounting principle for building differentially private programs. It is based on a simple generalisation of classic differential privacy which we call Personalised Differential Privacy, in which each individual has its own personal privacy budget. We will describe how this can be implemented in an interactive query system using the concept of lineage tracing from database theory.
(Describing joint work with Hamid Ebadi and Gerardo Schneider)