This explainer document aims to provide an overview of the current state of the rapidly
expanding work on synthetic data technologies, with a particular focus on privacy. The …

Differential privacy is a strong notion for privacy that can be used to prove formal
guarantees, in terms of a privacy budget, ε, about how much information is leaked by a …

Differential privacy has become a widely popular method for data protection in machine
learning, especially since it allows formulating strict mathematical privacy guarantees. This …

For many critical applications ranging from health care to social sciences, releasing
personal data while protecting individual privacy is paramount. Over the years, data …

As the prevalence of data analysis grows, safeguarding data privacy has become a
paramount concern. Consequently, there has been an upsurge in the development of …

Diffusion models (DMs) are one of the most widely used generative models for producing
high quality images. However, a flurry of recent papers points out that DMs are least private …

Increasing numbers of artificial intelligence systems are employing collaborative machine
learning techniques, such as federated learning, to build a shared powerful deep model …

How can we release a massive volume of sensitive data while mitigating privacy risks?
Privacy-preserving data synthesis enables the data holder to outsource analytical tasks to …

Training even moderately-sized generative models with differentially-private stochastic
gradient descent (DP-SGD) is difficult: the required level of noise for reasonable levels of …

This paper discusses how two classes of approximate computation algorithms can be
adapted, in a modular fashion, to achieve exact statistical inference from differentially private …