Related papers: Privacy Amplification for BandMF via $b$-Min-Sep S…

When applied to large-scale learning problems, the conventional wisdom on privacy-preserving deep learning, known as Differential Private Stochastic Gradient Descent (DP-SGD), has met with limited success due to significant performance…

$\epsilon$-Differential privacy (DP) is a well-known privacy model that offers strong privacy guarantees. However, when applied to data releases, DP significantly deteriorates the analytical utility of the protected outcomes. To keep data…

We design a class of additive noise mechanisms that satisfy \((\varepsilon, \delta)\)-differential privacy (DP) for scalar, real-valued query functions with known sensitivities, with a particular focus on moderate and low-privacy regimes.…

Differentially private stochastic gradient descent (DP-SGD) is the standard algorithm for training machine learning models under differential privacy (DP). The most common DP-SGD privacy accountants rely on Poisson subsampling to ensure the…

This chapter is meant to be part of the book "Differential Privacy for Artificial Intelligence Applications." We give an introduction to the most important property of differential privacy -- composition: running multiple independent…

Differential privacy provides a rigorous framework to quantify data privacy, and has received considerable interest recently. A randomized mechanism satisfying $(\epsilon, \delta)$-differential privacy (DP) roughly means that, except with a…

Training generative models with differential privacy (DP) typically involves injecting noise into gradient updates or adapting the discriminator's training procedure. As a result, such approaches often struggle with hyper-parameter tuning…

A major challenge for machine learning is increasing the availability of data while respecting the privacy of individuals. Here we combine the provable privacy guarantees of the differential privacy framework with the flexibility of…

As the modern world becomes increasingly digitized and interconnected, distributed signal processing has proven to be effective in processing its large volume of data. However, a main challenge limiting the broad use of distributed signal…

The Differential Privacy (DP) literature often centers on meeting privacy constraints by introducing noise to the query, typically using a pre-specified parametric distribution model with one or two degrees of freedom. However, this…

Differential privacy is a widely accepted measure of privacy in the context of deep learning algorithms, and achieving it relies on a noisy training approach known as differentially private stochastic gradient descent (DP-SGD). DP-SGD…

Federated learning (FL) that enables edge devices to collaboratively learn a shared model while keeping their training data locally has received great attention recently and can protect privacy in comparison with the traditional centralized…

Introducing noise in the training of machine learning systems is a powerful way to protect individual privacy via differential privacy guarantees, but comes at a cost to utility. This work looks at whether the inherent randomness of…

Traditional differential privacy is independent of the data distribution. However, this is not well-matched with the modern machine learning context, where models are trained on specific data. As a result, achieving meaningful privacy…

Recent work of Erlingsson, Feldman, Mironov, Raghunathan, Talwar, and Thakurta [EFMRTT19] demonstrates that random shuffling amplifies differential privacy guarantees of locally randomized data. Such amplification implies substantially…

For scalable machine learning on large data sets, subsampling a representative subset is a common approach for efficient model training. This is often achieved through importance sampling, whereby informative data points are sampled more…

Estimating the probability density of a population while preserving the privacy of individuals in that population is an important and challenging problem that has received considerable attention in recent years. While the previous…

We present a comprehensive view of the relations among several privacy notions: differential privacy (DP) [1], Bayesian differential privacy (BDP) [2], semantic privacy (SP) [3], and membership privacy (MP) [4]. The results are organized…

This article presents DDP-SA, a scalable privacy-preserving federated learning framework that jointly leverages client-side local differential privacy (LDP) and full-threshold additive secret sharing (ASS) for secure aggregation. Unlike…

Prior work on differential privacy analysis of randomized SGD algorithms relies on composition theorems, where the implicit (unrealistic) assumption is that the internal state of the iterative algorithm is revealed to the adversary. As a…