中文
相关论文

相关论文: Optimal Differential Privacy Composition for Expon…

200 篇论文

Differential privacy (DP) provides rigorous privacy guarantees on individual's data while also allowing for accurate statistics to be conducted on the overall, sensitive dataset. To design a private system, first private algorithms must be…

密码学与安全 · 计算机科学 2020-11-19 Mark Cesar , Ryan Rogers

Differential Privacy (DP) is the leading approach to privacy preserving deep learning. As such, there are multiple efforts to provide drop-in integration of DP into popular frameworks. These efforts, which add noise to each gradient…

机器学习 · 统计学 2021-06-08 Mathias Lécuyer

Composition is a key feature of differential privacy. Well-known advanced composition theorems allow one to query a private database quadratically more times than basic privacy composition would permit. However, these results require that…

机器学习 · 计算机科学 2023-10-25 Justin Whitehouse , Aaditya Ramdas , Ryan Rogers , Zhiwei Steven Wu

The composition theorems of differential privacy (DP) allow data curators to combine different algorithms to obtain a new algorithm that continues to satisfy DP. However, new granularity notions (i.e., neighborhood definitions), data…

密码学与安全 · 计算机科学 2024-04-18 Patricia Guerra-Balboa , Àlex Miranda-Pascual , Javier Parra-Arnau , Thorsten Strufe

Differential privacy (DP) is a widely used notion for reasoning about privacy when publishing aggregate data. In this paper, we observe that certain DP mechanisms are amenable to a posteriori privacy analysis that exploits the fact that…

密码学与安全 · 计算机科学 2023-06-21 Valentin Hartmann , Vincent Bindschaedler , Alexander Bentkamp , Robert West

Differential privacy (DP) has become the gold standard for privacy-preserving data analysis, but its applicability can be limited in scenarios involving complex dependencies between sensitive information and datasets. To address this, we…

密码学与安全 · 计算机科学 2025-05-05 Tao Zhang , Bradley A. Malin , Netanel Raviv , Yevgeniy Vorobeychik

In the study of differential privacy, composition theorems (starting with the original paper of Dwork, McSherry, Nissim, and Smith (TCC'06)) bound the degradation of privacy when composing several differentially private algorithms. Kairouz,…

计算复杂性 · 计算机科学 2016-06-01 Jack Murtagh , Salil Vadhan

We give a fast algorithm to optimally compose privacy guarantees of differentially private (DP) algorithms to arbitrary accuracy. Our method is based on the notion of privacy loss random variables to quantify the privacy loss of DP…

数据结构与算法 · 计算机科学 2021-10-27 Sivakanth Gopi , Yin Tat Lee , Lukas Wutschitz

An interactive mechanism is an algorithm that stores a data set and answers adaptively chosen queries to it. The mechanism is called differentially private, if any adversary cannot distinguish whether a specific individual is in the data…

密码学与安全 · 计算机科学 2022-10-17 Xin Lyu

We initiate a study of the composition properties of interactive differentially private mechanisms. An interactive differentially private mechanism is an algorithm that allows an analyst to adaptively ask queries about a sensitive dataset,…

密码学与安全 · 计算机科学 2021-09-17 Salil Vadhan , Tianhao Wang

Data engineering often requires accuracy (utility) constraints on results, posing significant challenges in designing differentially private (DP) mechanisms, particularly under stringent privacy parameter $\epsilon$. In this paper, we…

密码学与安全 · 计算机科学 2024-12-17 Bo Jiang , Wanrong Zhang , Donghang Lu , Jian Du , Sagar Sharma , Qiang Yan

In this paper, we study the concurrent composition of interactive mechanisms with adaptively chosen privacy-loss parameters. In this setting, the adversary can interleave queries to existing interactive mechanisms, as well as create new…

密码学与安全 · 计算机科学 2025-05-30 Samuel Haney , Michael Shoemate , Grace Tian , Salil Vadhan , Andrew Vyrros , Vicki Xu , Wanrong Zhang

The exact composition of mechanisms for which two differential privacy (DP) constraints hold simultaneously is studied. The resulting privacy region admits an exact representation as a mixture over compositions of mechanisms of…

信息论 · 计算机科学 2026-04-16 Cemre Cadir , Salim Najib , Yanina Y. Shkel

The objective of differential privacy (DP) is to protect privacy by producing an output distribution that is indistinguishable between any two neighboring databases. However, traditional differentially private mechanisms tend to produce…

密码学与安全 · 计算机科学 2023-11-07 Kai Zhang , Yanjun Zhang , Ruoxi Sun , Pei-Wei Tsai , Muneeb Ul Hassan , Xin Yuan , Minhui Xue , Jinjun Chen

Differential privacy (DP) is a widely applied paradigm for releasing data while maintaining user privacy. Its success is to a large part due to its composition property that guarantees privacy even in the case of multiple data releases.…

密码学与安全 · 计算机科学 2022-09-29 Valentin Hartmann , Vincent Bindschaedler , Robert West

Differential Privacy (DP) is a family of definitions that bound the worst-case privacy leakage of a mechanism. One important feature of the worst-case DP guarantee is it naturally implies protections against adversaries with less prior…

密码学与安全 · 计算机科学 2025-07-14 Marika Swanberg , Meenatchi Sundaram Muthu Selva Annamalai , Jamie Hayes , Borja Balle , Adam Smith

In this paper we initiate the study of adaptive composition in differential privacy when the length of the composition, and the privacy parameters themselves can be chosen adaptively, as a function of the outcome of previously run analyses.…

密码学与安全 · 计算机科学 2021-08-09 Ryan Rogers , Aaron Roth , Jonathan Ullman , Salil Vadhan

In many practical applications of differential privacy, practitioners seek to provide the best privacy guarantees subject to a target level of accuracy. A recent line of work by Ligett et al. '17 and Whitehouse et al. '22 has developed such…

密码学与安全 · 计算机科学 2023-12-07 Ryan Rogers , Gennady Samorodnitsky , Zhiwei Steven Wu , Aaditya Ramdas

Privacy-preserving data analysis has become a central challenge in modern statistics. At the same time, a long-standing goal in statistics is the development of adaptive procedures -- methods that achieve near-optimal performance across…

统计理论 · 数学 2025-12-17 T. Tony Cai , Abhinav Chakraborty , Lasse Vuursteen

Differential privacy (DP) is a formal notion that restricts the privacy leakage of an algorithm when running on sensitive data, in which privacy-utility trade-off is one of the central problems in private data analysis. In this work, we…

机器学习 · 计算机科学 2025-03-18 Bo Li , Wei Wang , Peng Ye
‹ 上一页 1 2 3 10 下一页 ›