中文
相关论文

相关论文: Shortest Paths and Distances with Differential Pri…

200 篇论文

This paper considers the private release of statistics of disjoint subsets of a dataset, in the setting of data heterogeneity, where users could contribute more than one sample, with different users contributing potentially different…

密码学与安全 · 计算机科学 2025-03-26 V. Arvind Rameshwar , Anshoo Tandon

Modern machine learning algorithms aim to extract fine-grained information from data to provide accurate predictions, which often conflicts with the goal of privacy protection. This paper addresses the practical and theoretical importance…

机器学习 · 统计学 2023-07-17 Puyu Wang , Yunwen Lei , Yiming Ying , Ding-Xuan Zhou

Decision trees are interpretable models that are well-suited to non-linear learning problems. Much work has been done on extending decision tree learning algorithms with differential privacy, a system that guarantees the privacy of samples…

机器学习 · 计算机科学 2023-10-13 Daniël Vos , Jelle Vos , Tianyu Li , Zekeriya Erkin , Sicco Verwer

Differentially-private histograms have emerged as a key tool for location privacy. While past mechanisms have included theoretical & experimental analysis, it has recently been observed that much of the existing literature does not fully…

数据库 · 计算机科学 2017-02-21 Maryam Fanaeepour , Benjamin I. P. Rubinstein

Standard differential privacy imposes uniform privacy constraints across all features, overlooking the inherent distinction between sensitive and insensitive features in practice. In this paper, we introduce a relaxed definition of…

机器学习 · 计算机科学 2026-05-06 Tianyu Wang , Luhao Zhang , Rachel Cummings

We study the accuracy of differentially private mechanisms in the continual release model. A continual release mechanism receives a sensitive dataset as a stream of $T$ inputs and produces, after receiving each input, an accurate output on…

数据结构与算法 · 计算机科学 2022-01-12 Palak Jain , Sofya Raskhodnikova , Satchit Sivakumar , Adam Smith

The rise of massive networks across diverse domains necessitates sophisticated graph analytics, often involving sensitive data and raising privacy concerns. This paper addresses these challenges using local differential privacy (LDP), which…

数据结构与算法 · 计算机科学 2025-08-28 Pranay Mundra , Charalampos Papamanthou , Julian Shun , Quanquan C. Liu

This paper investigates the problem of forecasting multivariate aggregated human mobility while preserving the privacy of the individuals concerned. Differential privacy, a state-of-the-art formal notion, has been used as the privacy…

机器学习 · 计算机科学 2022-06-06 Héber H. Arcolezi , Jean-François Couchot , Denis Renaud , Bechara Al Bouna , Xiaokui Xiao

Graph Neural Networks (GNNs) are a popular technique for modelling graph-structured data and computing node-level representations via aggregation of information from the neighborhood of each node. However, this aggregation implies an…

机器学习 · 计算机科学 2022-08-30 Ameya Daigavane , Gagan Madan , Aditya Sinha , Abhradeep Guha Thakurta , Gaurav Aggarwal , Prateek Jain

Private inference refers to a two-party setting in which one has a model (e.g., a linear classifier), the other has data, and the model is to be applied over the data while safeguarding the privacy of both parties. In particular, models in…

信息论 · 计算机科学 2023-05-09 Zirui Deng , Netanel Raviv

Given a directed graph of nodes and edges connecting them, a common problem is to find the shortest path between any two nodes. Here we show that the shortest path distances can be found by a simple matrix inversion: If the edges are given…

数据结构与算法 · 计算机科学 2024-07-25 Zeyu Jing , Markus Meister

Much of the literature on differential privacy focuses on item-level privacy, where loosely speaking, the goal is to provide privacy per item or training example. However, recently many practical applications such as federated learning…

机器学习 · 计算机科学 2021-01-13 Yuhan Liu , Ananda Theertha Suresh , Felix Yu , Sanjiv Kumar , Michael Riley

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 show new lower bounds on the sample complexity of $(\varepsilon, \delta)$-differentially private algorithms that accurately answer large sets of counting queries. A counting query on a database $D \in (\{0,1\}^d)^n$ has the form "What…

密码学与安全 · 计算机科学 2018-10-25 Mark Bun , Jonathan Ullman , Salil Vadhan

Privacy-preserving data analysis is a rising challenge in contemporary statistics, as the privacy guarantees of statistical methods are often achieved at the expense of accuracy. In this paper, we investigate the tradeoff between…

机器学习 · 统计学 2020-11-11 T. Tony Cai , Yichen Wang , Linjun Zhang

To expand the toolbox available to network science, we study the isomorphism between distance and Fuzzy (proximity or strength) graphs. Distinct transitive closures in Fuzzy graphs lead to closures of their isomorphic distance graphs with…

社会与信息网络 · 计算机科学 2014-10-17 Tiago Simas , Luis M Rocha

We study $\left(\epsilon,\delta\right)$-differentially private algorithms for the problem of approximately computing the top singular vector of a matrix $A\in\mathbb{R}^{n\times d}$ where each row of $A$ is a data point in $\mathbb{R}^{d}$.…

数据结构与算法 · 计算机科学 2026-05-20 Ta Duy Nguyen , Alina Ene , Huy Le Nguyen

We consider the problem of empirical risk minimization given a database, using the gradient descent algorithm. We note that the function to be optimized may be non-convex, consisting of saddle points which impede the convergence of the…

机器学习 · 计算机科学 2021-01-19 Thulasi Tholeti , Sheetal Kalyani

Learning on graphs is becoming prevalent in a wide range of applications including social networks, robotics, communication, medicine, etc. These datasets belonging to entities often contain critical private information. The utilization of…

机器学习 · 计算机科学 2023-05-22 Nimesh Agrawal , Nikita Malik , Sandeep Kumar

Differential privacy (DP) is a rigorous notion of data privacy, used for private statistics. The canonical algorithm for differentially private mean estimation is to first clip the samples to a bounded range and then add noise to their…

‹ 上一页 1 8 9 10 下一页 ›