Abstract Machine learning algorithms, when applied to sensitive data, pose a distinct threat
to privacy. A growing body of prior work demonstrates that models produced by these …

Machine learning algorithms, when applied to sensitive data, pose a distinct threat to
privacy. A growing body of prior work demonstrates that models produced by these …

As machine learning becomes more widely used, the need to study its implications in
security and privacy becomes more urgent. Although the body of work in privacy has been …

Membership inference is one of the simplest privacy threats faced by machine learning
models that are trained on private sensitive data. In this attack, an adversary infers whether a …

Machine learning models are commonly trained on sensitive and personal data such as
pictures, medical records, financial records, etc. A serious breach of the privacy of this …

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 …

Machine learning models are prone to memorizing sensitive data, making them vulnerable
to membership inference attacks in which an adversary aims to guess if an input sample was …

This article reviews privacy challenges in machine learning and provides a critical overview
of the relevant research literature. The possible adversarial models are discussed, a wide …

Abstract Machine learning models trained on private datasets have been shown to leak their
private data. Recent work has found that the average data point is rarely leaked---it is often …

This paper studies defense mechanisms against model inversion (MI) attacks--a type of
privacy attacks aimed at inferring information about the training data distribution given the …