We give simpler, sparser, and faster algorithms for differentially private fine-tuning of large-
scale pre-trained language models, which achieve the state-of-the-art privacy versus utility …

In the past decade, differential privacy has seen remarkable success as a rigorous and
practical formalization of data privacy. This privacy definition and its divergence based …

Abstract “Concentrated differential privacy” was recently introduced by Dwork and Rothblum
as a relaxation of differential privacy, which permits sharper analyses of many privacy …

Convex empirical risk minimization is a basic tool in machine learning and statistics. We
provide new algorithms and matching lower bounds for differentially private convex …

For many differentially private algorithms, such as the prominent noisy stochastic gradient
descent (DP-SGD), the analysis needed to bound the privacy leakage of a single training …

Differential privacy is a theoretical framework for ensuring the privacy of individual-level data
when performing statistical analysis of privacy-sensitive datasets. This tutorial provides an …

Adaptivity is an important feature of data analysis-the choice of questions to ask about a
dataset often depends on previous interactions with the same dataset. However, statistical …

We present a rigorous methodology for auditing differentially private machine learning by
adding multiple carefully designed examples called canaries. We take a first principles …

The cost of privacy: Optimal rates of convergence for parameter estimation with differential
privacy Page 1 The Annals of Statistics 2021, Vol. 49, No. 5, 2825–2850 https://doi.org/10.1214/21-AOS2058 …

Modern machine learning models are complex and frequently encode surprising amounts of
information about individual inputs. In extreme cases, complex models appear to memorize …