中文
相关论文

相关论文: R\'enyi Differential Privacy of the Sampled Gaussi…

200 篇论文

The Gaussian Mechanism (GM), which consists in adding Gaussian noise to a vector-valued query before releasing it, is a standard privacy protection mechanism. In particular, given that the query respects some L2 sensitivity property (the L2…

机器学习 · 计算机科学 2024-03-20 Hadrien Hendrikx , Paul Mangold , Aurélien Bellet

Communication cost and privacy are two major considerations in federated learning (FL). For communication cost, gradient compression by sketching the clients' transmitted model updates is often used for reducing per-round communication. For…

机器学习 · 计算机科学 2025-09-11 Qiaobo Li , Zhijie Chen , Arindam Banerjee

Differential privacy is a useful tool to build machine learning models which do not release too much information about the training data. We study the R\'enyi differential privacy of stochastic gradient descent when each training example is…

机器学习 · 计算机科学 2020-02-18 Eloïse Berthier , Sai Praneeth Karimireddy

In this paper, we propose a novel Heterogeneous Gaussian Mechanism (HGM) to preserve differential privacy in deep neural networks, with provable robustness against adversarial examples. We first relax the constraint of the privacy budget in…

密码学与安全 · 计算机科学 2019-06-05 NhatHai Phan , Minh Vu , Yang Liu , Ruoming Jin , Dejing Dou , Xintao Wu , My T. Thai

We study the problem of subsampling in differential privacy (DP), a question that is the centerpiece behind many successful differentially private machine learning algorithms. Specifically, we provide a tight upper bound on the R\'enyi…

机器学习 · 计算机科学 2018-12-05 Yu-Xiang Wang , Borja Balle , Shiva Kasiviswanathan

We study Gaussian mechanism in the shuffle model of differential privacy (DP). Particularly, we characterize the mechanism's R\'enyi differential privacy (RDP), showing that it is of the form: $$ \epsilon(\lambda) \leq…

密码学与安全 · 计算机科学 2023-07-05 Seng Pei Liew , Tsubasa Takahashi

Differentially Private Stochastic Gradient Descent (DP-SGD) is widely used to protect training data in machine learning. Its privacy guarantee is commonly analyzed through a security game in which an adversary infers whether a target record…

密码学与安全 · 计算机科学 2026-05-18 Wenhao Wang , Shujie Cui , Hui Cui , Xingliang Yuan

Gaussian sketching, which consists of pre-multiplying the data with a random Gaussian matrix, is a widely used technique for multiple problems in data science and machine learning, with applications spanning computationally efficient…

机器学习 · 计算机科学 2025-06-05 Omri Lev , Vishwak Srinivasan , Moshe Shenfeld , Katrina Ligett , Ayush Sekhari , Ashia C. Wilson

Differential privacy via output perturbation has been a de facto standard for releasing query or computation results on sensitive data. However, we identify that all existing Gaussian mechanisms suffer from the curse of full-rank covariance…

密码学与安全 · 计算机科学 2024-03-15 Tianxi Ji , Pan Li

The wide deployment of machine learning in recent years gives rise to a great demand for large-scale and high-dimensional data, for which the privacy raises serious concern. Differential privacy (DP) mechanisms are conventionally developed…

密码学与安全 · 计算机科学 2021-05-03 Jungang Yang , Liyao Xiang , Weiting Li , Wei Liu , Xinbing Wang

Differential privacy (DP) is obtained by randomizing a data analysis algorithm, which necessarily introduces a tradeoff between its utility and privacy. Many DP mechanisms are built upon one of two underlying tools: Laplace and Gaussian…

机器学习 · 计算机科学 2026-04-03 Roy Rinberg , Ilia Shumailov , Vikrant Singhal , Rachel Cummings , Nicolas Papernot

Learning often involves sensitive data and as such, privacy preserving extensions to Stochastic Gradient Descent (SGD) and other machine learning algorithms have been developed using the definitions of Differential Privacy (DP). In…

机器学习 · 计算机科学 2021-10-14 Friedrich Dörmann , Osvald Frisk , Lars Nørvang Andersen , Christian Fischer Pedersen

We introduce the multi-dimensional Skellam mechanism, a discrete differential privacy mechanism based on the difference of two independent Poisson random variables. To quantify its privacy guarantees, we analyze the privacy loss…

机器学习 · 计算机科学 2021-11-01 Naman Agarwal , Peter Kairouz , Ziyu Liu

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…

机器学习 · 统计学 2022-10-18 Jiayuan Ye , Reza Shokri

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…

机器学习 · 统计学 2019-01-18 Michael Thomas Smith , Max Zwiessele , Neil D. Lawrence

The Gaussian mechanism is one differential privacy mechanism commonly used to protect numerical data. However, it may be ill-suited to some applications because it has unbounded support and thus can produce invalid numerical answers to…

密码学与安全 · 计算机科学 2022-12-01 Bo Chen , Matthew Hale

Gaussian processes (GPs) are non-parametric Bayesian models that are widely used for diverse prediction tasks. Previous work in adding strong privacy protection to GPs via differential privacy (DP) has been limited to protecting only the…

机器学习 · 计算机科学 2021-11-12 Antti Honkela , Laila Melkas

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 that the original analysis has several important…

机器学习 · 计算机科学 2018-06-08 Borja Balle , Yu-Xiang Wang

A key tool for building differentially private systems is adding Gaussian noise to the output of a function evaluated on a sensitive dataset. Unfortunately, using a continuous distribution presents several practical challenges. First and…

数据结构与算法 · 计算机科学 2024-11-19 Clément L. Canonne , Gautam Kamath , Thomas Steinke

We consider the privacy amplification properties of a sampling scheme in which a user's data is used in k steps chosen randomly and uniformly from a sequence (or set) of t steps. This sampling scheme has been recently applied in the context…

机器学习 · 计算机科学 2026-01-16 Vitaly Feldman , Moshe Shenfeld
‹ 上一页 1 2 3 10 下一页 ›