中文
相关论文

相关论文: Optimizing Noise for $f$-Differential Privacy via …

200 篇论文

Perhaps the single most important use case for differential privacy is to privately answer numerical queries, which is usually achieved by adding noise to the answer vector. The central question, therefore, is to understand which noise…

机器学习 · 统计学 2021-03-17 Jinshuo Dong , Weijie J. Su , Linjun Zhang

Differential privacy is a formal mathematical {stand-ard} for quantifying the degree of that individual privacy in a statistical database is preserved. To guarantee differential privacy, a typical method is adding random noise to the…

信息论 · 计算机科学 2017-03-08 Jianping He , Lin Cai

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

This paper proposes a locally differentially private federated learning algorithm for strongly convex but possibly nonsmooth problems that protects the gradients of each worker against an honest but curious server. The proposed algorithm…

机器学习 · 计算机科学 2023-08-03 Jiaojiao Zhang , Dominik Fay , Mikael Johansson

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…

密码学与安全 · 计算机科学 2023-07-06 Gokularam Muthukrishnan , Sheetal Kalyani

Data privacy is an important concern in learning, when datasets contain sensitive information about individuals. This paper considers consensus-based distributed optimization under data privacy constraints. Consensus-based optimization…

机器学习 · 计算机科学 2019-03-20 Mehrdad Showkatbakhsh , Can Karakus , Suhas Diggavi

Our work focuses on understanding the underpinning mechanism of dataset condensation by drawing connections with ($\epsilon$, $\delta$)-differential privacy where the optimal noise, $\epsilon$, is chosen by adversarial uncertainty…

密码学与安全 · 计算机科学 2024-02-19 Kenneth Odoh

We consider a federated data analytics problem in which a server coordinates the collaborative data analysis of multiple users with privacy concerns and limited communication capability. The commonly adopted compression schemes introduce…

密码学与安全 · 计算机科学 2024-02-02 Richeng Jin , Zhonggen Su , Caijun Zhong , Zhaoyang Zhang , Tony Quek , Huaiyu Dai

We characterize the minimum noise amplitude and power for noise-adding mechanisms in $(\epsilon, \delta)$-differential privacy for single real-valued query function. We derive new lower bounds using the duality of linear programming, and…

密码学与安全 · 计算机科学 2019-02-06 Quan Geng , Wei Ding , Ruiqi Guo , Sanjiv Kumar

In this paper, we define noiseless privacy, as a non-stochastic rival to differential privacy, requiring that the outputs of a mechanism (i.e., function composition of a privacy-preserving mapping and a query) can attain only a few values…

信息论 · 计算机科学 2019-10-30 Farhad Farokhi

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.…

密码学与安全 · 计算机科学 2026-05-28 Huikang Liu , Aras Selvi , Wolfram Wiesemann

Differential privacy (DP) and local differential privacy (LPD) are frameworks to protect sensitive information in data collections. They are both based on obfuscation. In DP the noise is added to the result of queries on the dataset,…

密码学与安全 · 计算机科学 2019-07-01 Natasha Fernandes , Kacem Lefki , Catuscia Palamidessi

The Quantum Fisher Information (QFI) metric governs a fundamental duality: it quantifies both how precisely a parameter can be estimated (metrology) and how distinguishable two quantum states are (privacy). We exploit this duality to…

Differential privacy (DP), provides a framework for provable privacy protection against arbitrary adversaries, while allowing the release of summary statistics and synthetic data. We address the problem of releasing a noisy real-valued…

统计方法学 · 统计学 2024-11-04 Jordan Awan , Aleksandra Slavkovic

Language models are capable of memorizing detailed patterns and information, leading to a double-edged effect: they achieve impressive modeling performance on downstream tasks with the stored knowledge but also raise significant privacy…

人工智能 · 计算机科学 2024-10-07 Xianzhi Li , Ran Zmigrod , Zhiqiang Ma , Xiaomo Liu , Xiaodan Zhu

Privacy protection and nonconvexity are two challenging problems in decentralized optimization and learning involving sensitive data. Despite some recent advances addressing each of the two problems separately, no results have been reported…

最优化与控制 · 数学 2022-12-16 Yongqiang Wang , Tamer Basar

We propose a new dynamic average consensus algorithm that is robust to information-sharing noise arising from differential-privacy design. Not only is dynamic average consensus widely used in cooperative control and distributed tracking, it…

密码学与安全 · 计算机科学 2023-07-13 Yongqiang Wang

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

Federated learning, in which training data is distributed among users and never shared, has emerged as a popular approach to privacy-preserving machine learning. Cryptographic techniques such as secure aggregation are used to aggregate…

机器学习 · 计算机科学 2022-03-08 Rasmus Pagh , Nina Mesing Stausholm

Adding random noise to database query results is an important tool for achieving privacy. A challenge is to minimize this noise while still meeting privacy requirements. Recently, a sufficient and necessary condition for $(\epsilon,…

密码学与安全 · 计算机科学 2026-01-28 Staal A. Vinterbo