Consider a setting where multiple parties holding sensitive data aim to
...
Generating synthetic data, with or without differential privacy, has
att...
There has been significant recent progress in training differentially pr...
Differentially private (DP) release of multidimensional statistics typic...
Individual privacy accounting enables bounding differential privacy (DP)...
Learning a privacy-preserving model from distributed sensitive data is a...
While generation of synthetic data under differential privacy (DP) has
r...
In recent years, local differential privacy (LDP) has emerged as a techn...
Markov chain Monte Carlo (MCMC) algorithms have long been the main workh...
Shuffle model of differential privacy is a novel distributed privacy mod...
Gaussian processes (GPs) are non-parametric Bayesian models that are wid...
We present d3p, a software package designed to help fielding runtime
eff...
The recently proposed Fast Fourier Transform (FFT)-based accountant for
...
The framework of differential privacy (DP) upper bounds the information
...
In this work, we present a method for differentially private data sharin...
Strict privacy is of paramount importance in distributed machine learnin...
We propose a numerical accountant for evaluating the tight
(ε,δ)-privacy...
Differential privacy allows quantifying privacy loss from computations o...
In many real-world applications of machine learning, data are distribute...
Quantification of the privacy loss associated with a randomised algorith...
Recent developments in differentially private (DP) machine learning and ...
Motivation: Human genomic datasets often contain sensitive information t...
Differentially private learning has recently emerged as the leading appr...
Many applications of machine learning, for example in health care, would...
Many machine learning applications are based on data collected from peop...
Users of a personalised recommendation system face a dilemma: recommenda...
Various ℓ_1-penalised estimation methods such as graphical lasso and
CLI...
We present techniques for effective Gaussian process (GP) modelling of
m...
A software library for constructing and learning probabilistic models is...