SoK: Let The Privacy Games Begin! A Unified Treatment of Data Inference Privacy in Machine Learning

Abstract

Deploying machine learning models in production may allow adversaries to infer sensitive information about training data. There is a vast literature analyzing different types of inference risks, ranging from membership inference to reconstruction attacks. Inspired by the success of games (i.e., probabilistic experiments) to study security properties in cryptography, some authors describe privacy inference risks in machine learning using a similar game-based style. However, adversary capabilities and goals are often stated in subtly different ways from one presentation to the other, which makes it hard to relate and compose results. In this paper, we present a game-based framework to systematize the body of knowledge on privacy inference risks in machine learning.

Publication
In IEEE Symposium on Security and Privacy (S&P), 2023
Anshuman Suri
Anshuman Suri
Postdoc

My research interests include privacy and security in machine learning.

Related