Federated learning (FL) has attracted significant interest given its prominent advantages and
applicability in many scenarios. However, it has been demonstrated that sharing updated …

Reinforcement learning algorithms are widely used in domains where it is desirable to
provide a personalized service. In these domains it is common that user data contains …

Data analyses are usually designed to identify some property of the population from which
the data are drawn, generalizing beyond the specific data sample. For this reason, data …

Ensuring that analyses performed on a dataset are representative of the entire population is
one of the central problems in statistics. Most classical techniques assume that the dataset is …

Composition theorems are general and powerful tools that facilitate privacy accounting
across multiple data accesses from per-access privacy bounds. However they often result in …

In adaptive data analysis, a mechanism gets $ n $ iid samples from an unknown distribution
$\cal {D} $, andis required to provide accurate estimations to a sequence of adaptively …

We study the problem of releasing the weights of all-pairs shortest paths in a weighted
undirected graph with differential privacy (DP). In this setting, the underlying graph is fixed …

Data-dependent privacy accounting frameworks such as per-instance differential privacy
(pDP) and Fisher information loss (FIL) confer fine-grained privacy guarantees for …

In this work, we study the problem of answering $ k $ queries with $(\epsilon,\delta) $-
differential privacy, where each query has sensitivity one. We give an algorithm for this task …

As machine learning has become more relevant for everyday applications, a natural
requirement is the protection of the privacy of the training data. When the relevant learning …