中文
相关论文

相关论文: On the Generalization Properties of Differential P…

200 篇论文

Given a dataset of $n$ user-contributed strings, each of length at most $\ell$, a key problem is how to identify all frequent substrings while preserving each user's privacy. Recent work by Bernardini et al. (PODS'25) introduced a…

数据结构与算法 · 计算机科学 2026-03-11 Peaker Guo , Rayne Holland , Hao Wu

Privacy and communication constraints are two major bottlenecks in federated learning (FL) and analytics (FA). We study the optimal accuracy of mean and frequency estimation (canonical models for FL and FA respectively) under joint…

机器学习 · 统计学 2023-04-05 Wei-Ning Chen , Dan Song , Ayfer Ozgur , Peter Kairouz

We study the Densest Subgraph (DSG) problem under the additional constraint of differential privacy. DSG is a fundamental theoretical question which plays a central role in graph analytics, and so privacy is a natural requirement. All known…

数据结构与算法 · 计算机科学 2024-04-09 Michael Dinitz , Satyen Kale , Silvio Lattanzi , Sergei Vassilvitskii

The Shapley value has been proposed as a solution to many applications in machine learning, including for equitable valuation of data. Shapley values are computationally expensive and involve the entire dataset. The query for a point's…

机器学习 · 计算机科学 2022-06-02 Lauren Watson , Rayna Andreeva , Hao-Tsung Yang , Rik Sarkar

We study the problem of releasing the weights of all-pair shortest paths in a weighted undirected graph with differential privacy (DP). In this setting, the underlying graph is fixed and two graphs are neighbors if their edge weights differ…

数据结构与算法 · 计算机科学 2022-03-31 Badih Ghazi , Ravi Kumar , Pasin Manurangsi , Jelani Nelson

Differential Privacy (DP) is the current gold-standard for ensuring privacy for statistical queries. Estimation problems under DP constraints appearing in the literature have largely focused on providing equal privacy to all users. We…

机器学习 · 计算机科学 2025-04-22 Syomantak Chaudhuri , Thomas A. Courtade

We propose, implement, and evaluate a new algorithm for releasing answers to very large numbers of statistical queries like $k$-way marginals, subject to differential privacy. Our algorithm makes adaptive use of a continuous relaxation of…

机器学习 · 计算机科学 2021-06-24 Sergul Aydore , William Brown , Michael Kearns , Krishnaram Kenthapadi , Luca Melis , Aaron Roth , Ankit Siva

We propose an algorithm with improved query-complexity for the problem of hypothesis selection under local differential privacy constraints. Given a set of $k$ probability distributions $Q$, we describe an algorithm that satisfies local…

数据结构与算法 · 计算机科学 2026-01-16 Gautam Kamath , Alireza F. Pour , Matthew Regehr , David P. Woodruff

Consider updates arriving online in which the $t$th input is $(i_t,d_t)$, where $i_t$'s are thought of as IDs of users. Informally, a randomized function $f$ is {\em differentially private} with respect to the IDs if the probability…

密码学与安全 · 计算机科学 2010-09-09 Darakhshan Mir , S. Muthukrishnan , Aleksandar Nikolov , Rebecca N. Wright

We develop differentially private methods for estimating various distributional properties. Given a sample from a discrete distribution $p$, some functional $f$, and accuracy and privacy parameters $\alpha$ and $\varepsilon$, the goal is to…

数据结构与算法 · 计算机科学 2018-03-02 Jayadev Acharya , Gautam Kamath , Ziteng Sun , Huanyu Zhang

We study the fundamental problems of identity testing (goodness of fit), and closeness testing (two sample test) of distributions over $k$ elements, under differential privacy. While the problems have a long history in statistics, finite…

机器学习 · 计算机科学 2017-11-01 Jayadev Acharya , Ziteng Sun , Huanyu Zhang

We present a new locally differentially private algorithm for the heavy hitters problem which achieves optimal worst-case error as a function of all standardly considered parameters. Prior work obtained error rates which depend optimally on…

数据结构与算法 · 计算机科学 2017-11-15 Mark Bun , Jelani Nelson , Uri Stemmer

Adaptivity is an important feature of data analysis---the choice of questions to ask about a dataset often depends on previous interactions with the same dataset. However, statistical validity is typically studied in a nonadaptive model,…

机器学习 · 计算机科学 2015-11-10 Raef Bassily , Kobbi Nissim , Adam Smith , Thomas Steinke , Uri Stemmer , Jonathan Ullman

With the development of big data and machine learning, privacy concerns have become increasingly critical, especially when handling heterogeneous datasets containing sensitive personal information. Differential privacy provides a rigorous…

机器学习 · 统计学 2025-08-08 Ziliang Shen , Caixing Wang , Shaoli Wang , Yibo Yan

Recently differential privacy has been used for a number of streaming, data structure, and dynamic graph problems as a means of hiding the internal randomness of the data structure, so that multiple possibly adaptive queries can be made…

数据结构与算法 · 计算机科学 2025-06-09 Shiyuan Feng , Ying Feng , George Z. Li , Zhao Song , David P. Woodruff , Lichen Zhang

The Horvitz-Thompson estimate of a total can be seen as as differentially private mechanism applied to this population total. We provide forumlae to compute the $\epsilon$ and $\delta$ parameter for this specific mecanism, coupled or not…

统计理论 · 数学 2025-06-18 Daniel Bernard Bonnéry , Julien Jamme

The explosion in volume and variety of data offers enormous potential for research and commercial use. Increased availability of personal data is of particular interest in enabling highly customised services tuned to individual needs.…

密码学与安全 · 计算机科学 2017-10-05 Naoise Holohan , Spiros Antonatos , Stefano Braghin , Pól Mac Aonghusa

A central problem in differentially private data analysis is how to design efficient algorithms capable of answering large numbers of counting queries on a sensitive database. Counting queries of the form "What fraction of individual…

密码学与安全 · 计算机科学 2013-10-02 Jonathan Ullman

We study the problem of differentially private (DP) mechanisms for representing sets of size $k$ from a large universe. Our first construction creates $(\epsilon,\delta)$-DP representations with error probability of $1/(e^\epsilon + 1)$…

密码学与安全 · 计算机科学 2025-07-23 Sarvar Patel , Giuseppe Persiano , Joon Young Seo , Kevin Yeo

Differential privacy is a de facto standard for statistical computations over databases that contain private data. The strength of differential privacy lies in a rigorous mathematical definition that guarantees individual privacy and yet…

密码学与安全 · 计算机科学 2020-05-05 Gilles Barthe , Rohit Chadha , Vishal Jagannath , A. Prasad Sistla , Mahesh Viswanathan