Membership inference (MI) attacks mainly aim to infer whether a data record was used to
train a target model or not. Due to the serious privacy risks, MI attacks have been attracting a …

Privacy-preserving machine learning algorithms are crucial for the increasingly common
setting in which personal data, such as medical or financial records, are analyzed. We …

Learning problems form an important category of computational tasks that generalizes many
of the computations researchers apply to large real-life data sets. We ask, What concept …

Shortly after it was first introduced in 2006, differential privacy became the flagship data
privacy definition. Since then, numerous variants and extensions were proposed to adapt it …

In this article, we introduce a new and general privacy framework called Pufferfish. The
Pufferfish framework can be used to create new privacy definitions that are customized to the …

This paper investigates the problem of model aggregation for the federated learning aided
by multiple intelligent reflecting surfaces (IRSs). Since the local parameters are transmitted …

We study statistical risk minimization problems under a privacy model in which the data is
kept confidential even from the learner. In this local privacy framework, we establish sharp …

We design differentially private algorithms for statistical model selection. Given a data set
and a large, discrete collection of “models”, each of which is a family of probability …

The principal components analysis (PCA) algorithm is a standard tool for identifying good
low-dimensional approximations to high-dimensional data. Many data sets of interest …

In this paper we introduce a new and general privacy framework called Pufferfish. The
Pufferfish framework can be used to create new privacy definitions that are customized to the …