English
Related papers

Related papers: Fully Adaptive Composition for Gaussian Differenti…

200 papers

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…

Machine Learning · Computer Science 2023-10-25 Justin Whitehouse , Aaditya Ramdas , Ryan Rogers , Zhiwei Steven Wu

Federated learning is distributed model training across several clients without disclosing raw data. Despite advancements in data privacy, risks still remain. Differential Privacy (DP) is a technique to protect sensitive data by adding…

Machine Learning · Computer Science 2025-10-14 Tejash Varsani

Gaussian differential privacy (GDP) is a single-parameter family of privacy notions that provides coherent guarantees to avoid the exposure of sensitive individual information. Despite the extra interpretability and tighter bounds under…

Cryptography and Security · Computer Science 2022-10-18 Yi Liu , Ke Sun , Linglong Kong , Bei Jiang

A major challenge for machine learning is increasing the availability of data while respecting the privacy of individuals. Here we combine the provable privacy guarantees of the differential privacy framework with the flexibility of…

Machine Learning · Statistics 2019-01-18 Michael Thomas Smith , Max Zwiessele , Neil D. Lawrence

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…

Cryptography and Security · Computer Science 2023-08-25 Antti Koskela , Marlon Tobaben , Antti Honkela

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…

Machine Learning · Computer Science 2018-06-08 Borja Balle , Yu-Xiang Wang

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…

Cryptography and Security · Computer Science 2019-12-10 Jun Zhao , Teng Wang , Tao Bai , Kwok-Yan Lam , Zhiying Xu , Shuyu Shi , Xuebin Ren , Xinyu Yang , Yang Liu , Han Yu

Accounting for privacy loss under fully adaptive composition -- where mechanism choice and privacy parameters may depend on the history of prior outputs -- is a central challenge in differential privacy (DP). Here, privacy filters are…

Cryptography and Security · Computer Science 2026-05-13 Long Tran , Antti Koskela , Ossi Räisä , Antti Honkela

We design a class of additive noise mechanisms that satisfy \((\varepsilon, \delta)\)-differential privacy (DP) for scalar, real-valued query functions with known sensitivities, with a particular focus on moderate and low-privacy regimes.…

Cryptography and Security · Computer Science 2026-05-28 Huikang Liu , Aras Selvi , Wolfram Wiesemann

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…

Cryptography and Security · Computer Science 2023-12-07 Ryan Rogers , Gennady Samorodnitsky , Zhiwei Steven Wu , Aaditya Ramdas

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…

Data Structures and Algorithms · Computer Science 2024-11-19 Clément L. Canonne , Gautam Kamath , Thomas Steinke

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.…

Cryptography and Security · Computer Science 2021-08-09 Ryan Rogers , Aaron Roth , Jonathan Ullman , Salil Vadhan

Gaussian processes (GPs) are non-parametric Bayesian models that are widely used for diverse prediction tasks. Previous work in adding strong privacy protection to GPs via differential privacy (DP) has been limited to protecting only the…

Machine Learning · Computer Science 2021-11-12 Antti Honkela , Laila Melkas

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…

Cryptography and Security · Computer Science 2024-04-18 Patricia Guerra-Balboa , Àlex Miranda-Pascual , Javier Parra-Arnau , Thorsten Strufe

Composition is one of the most important properties of differential privacy (DP), as it allows algorithm designers to build complex private algorithms from DP primitives. We consider precise composition bounds of the overall privacy loss…

Cryptography and Security · Computer Science 2020-06-26 Jinshuo Dong , David Durfee , Ryan Rogers

This paper develops a framework for differentially private $e$-values under Gaussian differential privacy ($\mu$-GDP). We characterize the canonical noise mechanism, establishing that optimal multiplicative perturbation follows a Gaussian…

Methodology · Statistics 2026-05-29 Qi Kuang , Bowen Gang , Yin Xia

Datasets containing sensitive information are often sequentially analyzed by many algorithms. This raises a fundamental question in differential privacy regarding how the overall privacy bound degrades under composition. To address this…

Machine Learning · Statistics 2020-03-26 Qinqing Zheng , Jinshuo Dong , Qi Long , Weijie J. Su

The framework of differential privacy protects an individual's privacy while publishing query responses on congregated data. In this work, a new noise addition mechanism for differential privacy is introduced where the noise added is…

Cryptography and Security · Computer Science 2023-07-06 Gokularam Muthukrishnan , Sheetal Kalyani

Differential privacy (DP) is obtained by randomizing a data analysis algorithm, which necessarily introduces a tradeoff between its utility and privacy. Many DP mechanisms are built upon one of two underlying tools: Laplace and Gaussian…

Machine Learning · Computer Science 2026-04-03 Roy Rinberg , Ilia Shumailov , Vikrant Singhal , Rachel Cummings , Nicolas Papernot

Learning often involves sensitive data and as such, privacy preserving extensions to Stochastic Gradient Descent (SGD) and other machine learning algorithms have been developed using the definitions of Differential Privacy (DP). In…

Machine Learning · Computer Science 2021-10-14 Friedrich Dörmann , Osvald Frisk , Lars Nørvang Andersen , Christian Fischer Pedersen
‹ Prev 1 2 3 10 Next ›