Search Results for author:
Found 29 papers, 15 papers with code
Understanding Practical Membership Privacy of Deep Learning
We apply a state-of-the-art membership inference attack (MIA) to systematically test the practical privacy vulnerability of fine-tuning large image classification models. We focus on understanding the properties of data sets and samples that make them vulnerable to membership inference.
A Bias-Variance Decomposition for Ensembles over Multiple Synthetic Datasets
We investigate how our theory works in practice by evaluating the performance of an ensemble over many synthetic datasets for several real datasets and downstream predictors.
Subsampling is not Magic: Why Large Batch Sizes Work for Differentially Private Stochastic Optimisation
The remaining subsampling-induced variance decreases with larger batch sizes, so large batches reduce the effective total gradient variance.
Privacy-Aware Document Visual Question Answering
We employ a federated learning scheme, that reflects the real-life distribution of documents in different businesses, and we explore the use case where the ID of the invoice issuer is the sensitive information to be protected.
Collaborative Learning From Distributed Data With Differentially Private Synthetic Twin Data
Consider a setting where multiple parties holding sensitive data aim to collaboratively learn population level statistics, but pooling the sensitive data sets is not possible.
On the Efficacy of Differentially Private Few-shot Image Classification
There has been significant recent progress in training differentially private (DP) models which achieve accuracy that approaches the best non-private models.
DPVIm: Differentially Private Variational Inference Improved
Using this as prior knowledge we establish a link between the gradients of the variational parameters, and propose an efficient while simple fix for the problem to obtain a less noisy gradient estimator, which we call $\textit{aligned}$ gradients.
Individual Privacy Accounting with Gaussian Differential Privacy
In order to account for the individual privacy losses in a principled manner, we need a privacy accountant for adaptive compositions of randomised mechanisms, where the loss incurred at a given data access is allowed to be smaller than the worst-case loss.
Differentially private partitioned variational inference
In this paper, we present differentially private partitioned variational inference, the first general framework for learning a variational approximation to a Bayesian posterior distribution in the federated learning setting while minimising the number of communication rounds and providing differential privacy guarantees for data subjects.
Noise-Aware Statistical Inference with Differentially Private Synthetic Data
For example, confidence intervals become too narrow, which we demonstrate with a simple experiment.
Locally Differentially Private Bayesian Inference
In recent years, local differential privacy (LDP) has emerged as a technique of choice for privacy-preserving data collection in several scenarios when the aggregator is not trustworthy.
Gaussian Processes with Differential Privacy
We achieve this by using sparse GP methodology and publishing a private variational approximation on known inducing points.
Tight Accounting in the Shuffle Model of Differential Privacy
Shuffle model of differential privacy is a novel distributed privacy model based on a combination of local privacy mechanisms and a secure shuffler.
D3p -- A Python Package for Differentially-Private Probabilistic Programming
We present d3p, a software package designed to help fielding runtime efficient widely-applicable Bayesian inference under differential privacy guarantees.
Computing Differential Privacy Guarantees for Heterogeneous Compositions Using FFT
The recently proposed Fast Fourier Transform (FFT)-based accountant for evaluating $(\varepsilon,\delta)$-differential privacy guarantees using the privacy loss distribution formalism has been shown to give tighter bounds than commonly used methods such as R\'enyi accountants when applied to homogeneous compositions, i. e., to compositions of identical mechanisms.
Differentially Private Bayesian Inference for Generalized Linear Models
Generalized linear models (GLMs) such as logistic regression are among the most widely used arms in data analyst's repertoire and often used on sensitive datasets.
Privacy-preserving Data Sharing on Vertically Partitioned Data
We modify a secure multiparty computation (MPC) framework to combine MPC with differential privacy (DP), in order to use differentially private MPC effectively to learn a probabilistic generative model under DP on such vertically partitioned data.
Differentially private cross-silo federated learning
In this paper we combine additively homomorphic secure summation protocols with differential privacy in the so-called cross-silo federated learning setting.
Tight Differential Privacy for Discrete-Valued Mechanisms and for the Subsampled Gaussian Mechanism Using FFT
We carry out an error analysis of the method in terms of moment bounds of the privacy loss distribution which leads to rigorous lower and upper bounds for the true $(\varepsilon,\delta)$-values.
Privacy-preserving data sharing via probabilistic modelling
Differential privacy allows quantifying privacy loss resulting from accessing sensitive personal data.
Differentially Private Federated Variational Inference
This setting is known as federated learning, in which privacy is a key concern.
Computing Tight Differential Privacy Guarantees Using FFT
The privacy loss of DP algorithms is commonly reported using $(\varepsilon,\delta)$-DP.
Representation Transfer for Differentially Private Drug Sensitivity Prediction
Differentially private learning with genomic data is challenging because it is more difficult to guarantee the privacy in high dimensions.
Differentially Private Markov Chain Monte Carlo
Recent developments in differentially private (DP) machine learning and DP Bayesian learning have enabled learning under strong privacy guarantees for the training data subjects.
Learning Rate Adaptation for Federated and Differentially Private Learning
We also show that it works robustly in the case of federated learning unlike commonly used optimisation methods.
Differentially Private Bayesian Learning on Distributed Data
Many applications of machine learning, for example in health care, would benefit from methods that can guarantee privacy of data subjects.
Differentially Private Variational Inference for Non-conjugate Models
It is built on top of doubly stochastic variational inference, a recent advance which provides a variational solution to a large class of models.
Efficient differentially private learning improves drug sensitivity prediction
Good personalised predictions are vitally important in precision medicine, but genomic information on which the predictions are based is also particularly sensitive, as it directly identifies the patients and hence cannot easily be anonymised.
On the inconsistency of $\ell_1$-penalised sparse precision matrix estimation
Various $\ell_1$-penalised estimation methods such as graphical lasso and CLIME are widely used for sparse precision matrix estimation.
