SoK: Let the Privacy Games Begin! A Unified Treatment of Data Inference Privacy in Machine Learning
This work addresses a foundational issue for researchers and practitioners in privacy-preserving machine learning by providing a unified treatment to improve clarity and composability of results.
The paper tackles the problem of inconsistent definitions for data inference privacy risks in machine learning by proposing a game-based framework to systematize and unify these definitions, formally establishing known relations and uncovering new ones.
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. We use this framework to (1) provide a unifying structure for definitions of inference risks, (2) formally establish known relations among definitions, and (3) to uncover hitherto unknown relations that would have been difficult to spot otherwise.