The Gaussian mechanism is an essential building block used in multitude of differentially
private data analysis algorithms. In this paper we revisit the Gaussian mechanism and show …

This work studies differential privacy in the context of the recently proposed shuffle model.
Unlike in the local model, where the server collecting privatized data from users can track back …

Differential Privacy (DP) provides a formal privacy guarantee preventing adversaries with
access to a machine learning model from extracting information about individual training points…

We study the problem of subsampling in differential privacy (DP), a question that is the
centerpiece behind many successful differentially private machine learning algorithms. …

Weighted finite automata (WFA) are finite automata whose transitions and states are augmented
with some weights, elements of a semiring. A WFA induces a function over strings. The …

Differential privacy comes equipped with multiple analytical tools for the design of private
data analyses. One important tool is the so-called" privacy amplification by subsampling" …

Image diffusion models such as DALL-E 2, Imagen, and Stable Diffusion have attracted
significant attention due to their ability to generate high-quality synthetic images. In this work, we …

This paper aims to help structure the risk landscape associated with large-scale Language
Models (LMs). In order to foster advances in responsible innovation, an in-depth …

Given access to a machine learning model, can an adversary reconstruct the model’s training
data? This work studies this question from the lens of a powerful informed adversary who …

Responsible innovation on large-scale Language Models (LMs) requires foresight into and
in-depth understanding of the risks these models may pose. This paper develops a …