中文
相关论文

相关论文: Tight Differential Privacy for Discrete-Valued Mec…

200 篇论文

Differentially private (DP) machine learning has recently become popular. The privacy loss of DP algorithms is commonly reported using $(\varepsilon,\delta)$-DP. In this paper, we propose a numerical accountant for evaluating the privacy…

机器学习 · 统计学 2020-08-28 Antti Koskela , Joonas Jälkö , Antti Honkela

The verification of differential privacy algorithms that employ Gaussian distributions is little understood. This paper tackles the challenge of verifying such programs by introducing a novel approach to approximating probability…

密码学与安全 · 计算机科学 2025-09-11 Bishnu Bhusal , Rohit Chadha , A. Prasad Sistla , Mahesh Viswanathan

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…

密码学与安全 · 计算机科学 2021-06-22 Antti Koskela , Antti Honkela

Individual privacy accounting enables bounding differential privacy (DP) loss individually for each participant involved in the analysis. This can be informative as often the individual privacy losses are considerably smaller than those…

密码学与安全 · 计算机科学 2023-08-25 Antti Koskela , Marlon Tobaben , Antti Honkela

Shuffle model of differential privacy is a novel distributed privacy model based on a combination of local privacy mechanisms and a secure shuffler. It has been shown that the additional randomisation provided by the shuffler improves…

密码学与安全 · 计算机科学 2022-02-02 Antti Koskela , Mikko A. Heikkilä , Antti Honkela

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

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…

密码学与安全 · 计算机科学 2019-12-10 Jun Zhao , Teng Wang , Tao Bai , Kwok-Yan Lam , Zhiying Xu , Shuyu Shi , Xuebin Ren , Xinyu Yang , Yang Liu , Han Yu

Sparse histogram methods can be useful for returning differentially private counts of items in large or infinite histograms, large group-by queries, and more generally, releasing a set of statistics with sufficient item counts. We consider…

密码学与安全 · 计算机科学 2022-02-03 Brian Karrer , Daniel Kifer , Arjun Wilkins , Danfeng Zhang

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

Data-dependent privacy accounting frameworks such as per-instance differential privacy (pDP) and Fisher information loss (FIL) confer fine-grained privacy guarantees for individuals in a fixed training dataset. These guarantees can be…

密码学与安全 · 计算机科学 2024-03-12 Shengyuan Hu , Saeed Mahloujifar , Virginia Smith , Kamalika Chaudhuri , Chuan Guo

We present a novel method for accurately auditing the differential privacy (DP) guarantees of DP mechanisms. In particular, our solution is applicable to auditing DP guarantees of machine learning (ML) models. Previous auditing methods…

机器学习 · 计算机科学 2026-01-14 Antti Koskela , Jafar Mohammadi

The ratio of two Gaussians is useful in many contexts of statistical inference. We discuss statistically valid inference of the ratio under Differential Privacy (DP). We use the delta method to derive the asymptotic distribution of the…

统计方法学 · 统计学 2022-06-30 Jingang Miao , Yiming Paul Li

The Sampled Gaussian Mechanism (SGM)---a composition of subsampling and the additive Gaussian noise---has been successfully used in a number of machine learning applications. The mechanism's unexpected power is derived from privacy…

机器学习 · 计算机科学 2019-08-29 Ilya Mironov , Kunal Talwar , Li Zhang

In this work, we study high-dimensional mean estimation under user-level differential privacy, and design an $(\varepsilon,\delta)$-differentially private mechanism using as few users as possible. In particular, we provide a nearly optimal…

数据结构与算法 · 计算机科学 2022-06-14 Hossein Esfandiari , Vahab Mirrokni , Shyam Narayanan

In this work, we give efficient algorithms for privately estimating a Gaussian distribution in both pure and approximate differential privacy (DP) models with optimal dependence on the dimension in the sample complexity. In the pure DP…

数据结构与算法 · 计算机科学 2023-06-02 Daniel Alabi , Pravesh K. Kothari , Pranay Tankala , Prayaag Venkat , Fred Zhang

We characterize the minimum noise amplitude and power for noise-adding mechanisms in $(\epsilon, \delta)$-differential privacy for single real-valued query function. We derive new lower bounds using the duality of linear programming, and…

密码学与安全 · 计算机科学 2019-02-06 Quan Geng , Wei Ding , Ruiqi Guo , Sanjiv Kumar

The Gaussian distribution is widely used in mechanism design for differential privacy (DP). Thanks to its sub-Gaussian tail, it significantly reduces the chance of outliers when responding to queries. However, it can only provide…

密码学与安全 · 计算机科学 2021-10-14 Parastoo Sadeghi , Mehdi Korki

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

In this paper, we consider the problem of responding to a count query (or any other integer-valued queries) evaluated on a dataset containing sensitive attributes. To protect the privacy of individuals in the dataset, a standard practice is…

信息论 · 计算机科学 2020-07-21 Parastoo Sadeghi , Shahab Asoodeh , Flavio du Pin Calmon

Differentially private (DP) mechanisms face the challenge of providing accurate results while protecting their inputs: the privacy-utility trade-off. A simple but powerful technique for DP adds noise to sensitivity-bounded query outputs to…

密码学与安全 · 计算机科学 2021-07-28 David M. Sommer , Lukas Abfalterer , Sheila Zingg , Esfandiar Mohammadi
‹ 上一页 1 2 3 10 下一页 ›