中文
相关论文

相关论文: Interactive Privacy via the Median Mechanism

200 篇论文

Bayesian inference has great promise for the privacy-preserving analysis of sensitive data, as posterior sampling automatically preserves differential privacy, an algorithmic notion of data privacy, under certain conditions (Dimitrakakis et…

机器学习 · 计算机科学 2016-06-10 James Foulds , Joseph Geumlek , Max Welling , Kamalika Chaudhuri

For systems whose states implicate sensitive information, their privacy is of great concern. While notions like differential privacy have been successfully introduced to dynamical systems, it is still unclear how a system's privacy can be…

系统与控制 · 电气工程与系统科学 2025-11-17 Le Liu , Yu Kawano , Ming Cao

Differential privacy is achieved by the introduction of Laplacian noise in the response to a query, establishing a precise trade-off between the level of differential privacy and the accuracy of the database response (via the amount of…

数据库 · 计算机科学 2014-07-02 Maurizio Naldi , Giuseppe D'Acquisto

Differential privacy is widely adopted to provide provable privacy guarantees in data analysis. We consider the problem of combining public and private data (and, more generally, data with heterogeneous privacy needs) for estimating…

机器学习 · 计算机科学 2021-11-02 Cecilia Ferrando , Jennifer Gillenwater , Alex Kulesza

Many privacy mechanisms reveal high-level information about a data distribution through noisy measurements. It is common to use this information to estimate the answers to new queries. In this work, we provide an approach to solve this…

机器学习 · 计算机科学 2019-01-29 Ryan McKenna , Daniel Sheldon , Gerome Miklau

Consider a data publishing setting for a dataset composed by both private and non-private features. The publisher uses an empirical distribution, estimated from $n$ i.i.d. samples, to design a privacy mechanism which is applied to new fresh…

信息论 · 计算机科学 2020-03-23 Mario Diaz , Hao Wang , Flavio P. Calmon , Lalitha Sankar

Since being proposed in 2006, differential privacy has become a standard method for quantifying certain risks in publishing or sharing analyses of sensitive data. At its heart, differential privacy measures risk in terms of the differences…

信息论 · 计算机科学 2025-11-19 Anand D. Sarwate , Flavio P. Calmon , Oliver Kosut , Lalitha Sankar

The objective of machine learning is to extract useful information from data, while privacy is preserved by concealing information. Thus it seems hard to reconcile these competing interests. However, they frequently must be balanced when…

机器学习 · 计算机科学 2014-12-25 Zhanglong Ji , Zachary C. Lipton , Charles Elkan

We propose new differential privacy solutions for when external \emph{invariants} and \emph{integer} constraints are simultaneously enforced on the data product. These requirements arise in real world applications of private data curation,…

密码学与安全 · 计算机科学 2022-12-05 Prathamesh Dharangutte , Jie Gao , Ruobin Gong , Fang-Yi Yu

Detecting inference queries running over personal attributes and protecting such queries from leaking individual information requires tremendous effort from practitioners. To tackle this problem, we propose an end-to-end workflow for…

In this paper, we focus on developing a novel mechanism to preserve differential privacy in deep neural networks, such that: (1) The privacy budget consumption is totally independent of the number of training steps; (2) It has the ability…

密码学与安全 · 计算机科学 2018-04-24 NhatHai Phan , Xintao Wu , Han Hu , Dejing Dou

The rise of connected personal devices together with privacy concerns call for machine learning algorithms capable of leveraging the data of a large number of agents to learn personalized models under strong privacy requirements. In this…

机器学习 · 计算机科学 2018-02-20 Aurélien Bellet , Rachid Guerraoui , Mahsa Taziki , Marc Tommasi

In privacy-preserving machine learning, individual parties are reluctant to share their sensitive training data due to privacy concerns. Even the trained model parameters or prediction can pose serious privacy leakage. To address these…

密码学与安全 · 计算机科学 2020-09-04 Lingjuan Lyu , Yee Wei Law , Kee Siong Ng , Shibei Xue , Jun Zhao , Mengmeng Yang , Lei Liu

Rigorous privacy mechanisms that can cope with dynamic data are required to encourage a wider adoption of large-scale monitoring and decision systems relying on end-user information. A promising approach to develop these mechanisms is to…

数据库 · 计算机科学 2013-04-09 Jerome Le Ny

The randomized power method has gained significant interest due to its simplicity and efficient handling of large-scale spectral analysis and recommendation tasks. However, its application to large datasets containing personal information…

机器学习 · 计算机科学 2025-06-13 Julien Nicolas , César Sabater , Mohamed Maouche , Sonia Ben Mokhtar , Mark Coates

Artificial Intelligence (AI) has attracted a great deal of attention in recent years. However, alongside all its advancements, problems have also emerged, such as privacy violations, security issues and model fairness. Differential privacy,…

密码学与安全 · 计算机科学 2020-09-01 Tianqing Zhu , Dayong Ye , Wei Wang , Wanlei Zhou , Philip S. Yu

The Laplace mechanism and the Gaussian mechanism are primary mechanisms in differential privacy, widely applicable to many scenarios involving numerical data. However, due to the infinite-range random variables they generate, the Laplace…

密码学与安全 · 计算机科学 2023-09-25 Jie Fu , Zhiyu Sun , Haitao Liu , Zhili Chen

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

We address the problem of efficiently and effectively answering large numbers of queries on a sensitive dataset while ensuring differential privacy (DP). We separately analyze this problem in two distinct settings, grounding our work in a…

密码学与安全 · 计算机科学 2023-02-10 Brendan Avent , Aleksandra Korolova

A scheme that publishes aggregate information about sensitive data must resolve the trade-off between utility to information consumers and privacy of the database participants. Differential privacy is a well-established definition of…

密码学与安全 · 计算机科学 2010-01-18 Mangesh Gupte , Mukund Sundararajan