中文
相关论文

相关论文: Minimax Rates of Estimating Approximate Differenti…

200 篇论文

We study the relationship between two desiderata of algorithms in statistical inference and machine learning: differential privacy and robustness to adversarial data corruptions. Their conceptual similarity was first observed by Dwork and…

机器学习 · 计算机科学 2023-02-06 Hilal Asi , Jonathan Ullman , Lydia Zakynthinou

Differential privacy is widely considered the formal privacy for privacy-preserving data analysis due to its robust and rigorous guarantees, with increasingly broad adoption in public services, academia, and industry. Despite originating in…

统计理论 · 数学 2024-12-05 Weijie J. Su

In modern settings of data analysis, we may be running our algorithms on datasets that are sensitive in nature. However, classical machine learning and statistical algorithms were not designed with these risks in mind, and it has been…

数据结构与算法 · 计算机科学 2021-08-21 Huanyu Zhang

We investigate a problem of finding the minimum, in which each user has a real value and we want to estimate the minimum of these values under the local differential privacy constraint. We reveal that this problem is fundamentally…

统计理论 · 数学 2019-05-28 Kazuto Fukuchi , Chia-Mu Yu , Arashi Haishima , Jun Sakuma

We present a mechanism for computing asymptotically stable school optimal matchings, while guaranteeing that it is an asymptotic dominant strategy for every student to report their true preferences to the mechanism. Our main tool in this…

计算机科学与博弈论 · 计算机科学 2014-10-27 Sampath Kannan , Jamie Morgenstern , Aaron Roth , Zhiwei Steven Wu

In the field of machine learning, many problems can be formulated as the minimax problem, including reinforcement learning, generative adversarial networks, to just name a few. So the minimax problem has attracted a huge amount of…

机器学习 · 计算机科学 2022-04-25 Yilin Kang , Yong Liu , Jian Li , Weiping Wang

Popular approaches to differential privacy, such as the Laplace and exponential mechanisms, calibrate randomised smoothing through global sensitivity of the target non-private function. Bounding such sensitivity is often a prohibitively…

机器学习 · 计算机科学 2017-06-12 Benjamin I. P. Rubinstein , Francesco Aldà

Differential Privacy (DP) has become a gold standard in privacy-preserving data analysis. While it provides one of the most rigorous notions of privacy, there are many settings where its applicability is limited. Our main contribution is in…

密码学与安全 · 计算机科学 2021-10-20 Aman Bansal , Rahul Chunduru , Deepesh Data , Manoj Prabhakaran

Differential privacy is a rigorous privacy condition achieved by randomizing query answers. This paper develops efficient algorithms for answering multiple queries under differential privacy with low error. We pursue this goal by advancing…

数据库 · 计算机科学 2011-03-08 Chao Li , Gerome Miklau

Designing privacy-preserving machine learning algorithms has received great attention in recent years, especially in the setting when the data contains sensitive information. Differential privacy (DP) is a widely used mechanism for data…

机器学习 · 计算机科学 2025-09-11 Chunyang Liao , Deanna Needell , Hayden Schaeffer , Alexander Xue

Bounding privacy leakage over compositions, i.e., privacy accounting, is a key challenge in differential privacy (DP). The privacy parameter ($\eps$ or $\delta$) is often easy to estimate but hard to bound. In this paper, we propose a new…

密码学与安全 · 计算机科学 2023-11-22 Jiachen T. Wang , Saeed Mahloujifar , Tong Wu , Ruoxi Jia , Prateek Mittal

Training with differential privacy (DP) provides a guarantee to members in a dataset that they cannot be identified by users of the released model. However, those data providers, and, in general, the public, lack methods to efficiently…

机器学习 · 计算机科学 2025-12-04 Zoë Ruha Bell , Anvith Thudi , Olive Franzese-McLaughlin , Nicolas Papernot , Shafi Goldwasser

We revisit the problem of linear regression under a differential privacy constraint. By consolidating existing pieces in the literature, we clarify the correct dependence of the feature, label and coefficient domains in the optimization…

机器学习 · 统计学 2018-07-10 Yu-Xiang Wang

We study the problem of mean estimation of $\ell_2$-bounded vectors under the constraint of local differential privacy. While the literature has a variety of algorithms that achieve the asymptotically optimal rates for this problem, the…

机器学习 · 计算机科学 2022-05-06 Hilal Asi , Vitaly Feldman , Kunal Talwar

A wide variety of privacy metrics have been proposed in the literature to evaluate the level of protection offered by privacy enhancing-technologies. Most of these metrics are specific to concrete systems and adversarial models, and are…

信息论 · 计算机科学 2012-11-14 David Rebollo-Monedero , Javier Parra-Arnau , Claudia Diaz , Jordi Forné

We consider a refinement of differential privacy --- per instance differential privacy (pDP), which captures the privacy of a specific individual with respect to a fixed data set. We show that this is a strict generalization of the standard…

机器学习 · 统计学 2018-11-15 Yu-Xiang Wang

Differential privacy is a restriction on data processing algorithms that provides strong confidentiality guarantees for individual records in the data. However, research on proper statistical inference, that is, research on properly…

密码学与安全 · 计算机科学 2021-07-06 Joerg Drechsler , Ira Globus-Harris , Audra McMillan , Jayshree Sarathy , Adam Smith

In this paper, we consider the $k$-approximate pattern matching problem under differential privacy, where the goal is to report or count all substrings of a given string $S$ which have a Hamming distance at most $k$ to a pattern $P$, or…

数据结构与算法 · 计算机科学 2023-11-14 Teresa Anna Steiner

Protecting individual privacy is crucial when releasing sensitive data for public use. While data de-identification helps, it is not enough. This paper addresses parameter estimation in scenarios where data are perturbed using the…

统计方法学 · 统计学 2024-03-13 Qinglong Tian , Jiwei Zhao

Differential privacy offers formal quantitative guarantees for algorithms over datasets, but it assumes attackers that know and can influence all but one record in the database. This assumption often vastly overapproximates the attackers'…

密码学与安全 · 计算机科学 2020-12-01 Damien Desfontaines , Esfandiar Mohammadi , Elisabeth Krahmer , David Basin