Composition of Differential Privacy & Privacy Amplification by Subsampling
It addresses foundational concepts for ensuring privacy in AI applications, but is incremental as it summarizes existing results.
The chapter introduces composition and privacy amplification by subsampling in differential privacy, explaining that multiple private analyses remain private and providing proofs for practical application.
This chapter is meant to be part of the book "Differential Privacy for Artificial Intelligence Applications." We give an introduction to the most important property of differential privacy -- composition: running multiple independent analyses on the data of a set of people will still be differentially private as long as each of the analyses is private on its own -- as well as the related topic of privacy amplification by subsampling. This chapter introduces the basic concepts and gives proofs of the key results needed to apply these tools in practice.