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 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 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 …

Privacy attacks on machine learning models aim to identify the data that is used to train such
models. Such attacks, traditionally, are studied on static models that are trained once and …

We introduce a new class of attacks on machine learning models. We show that an
adversary who can poison a training dataset can cause models trained on this dataset to …

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 …

The recent, remarkable growth of machine learning has led to intense interest in the privacy
of the data on which machine learning relies, and to new techniques for preserving privacy …

The privacy risks of machine learning models is a major concern when training them on
sensitive and personal data. We discuss the tradeoffs between data privacy and the …

Advances in machine learning (ML) in recent years have enabled a dizzying array of
applications such as data analytics, autonomous systems, and security diagnostics. ML is …

The increasing adoption of machine learning inference in applications has led to a
corresponding increase in concerns about the privacy guarantees offered by existing …