English
Related papers

Related papers: Mutual Information Bounds in the Shuffle Model

200 papers

Differential Privacy (DP) mechanisms, especially in high-dimensional settings, often face the challenge of maintaining privacy without compromising the data utility. This work introduces an innovative shuffling mechanism in…

Machine Learning · Computer Science 2024-07-23 Jungang Yang , Zhe Ji , Liyao Xiang

Motivated by recent developments in the shuffle model of differential privacy, we propose a new approximate shuffling functionality called Alternating Shuffle, and provide a protocol implementing alternating shuffling in a single-server…

Cryptography and Security · Computer Science 2023-09-08 Borja Balle , James Bell , Adrià Gascón

The Differentially Private Stochastic Gradient Descent (DP-SGD) algorithm supports the training of machine learning (ML) models with formal Differential Privacy (DP) guarantees. Traditionally, DP-SGD processes training data in batches using…

Cryptography and Security · Computer Science 2025-12-15 Meenatchi Sundaram Muthu Selva Annamalai , Borja Balle , Jamie Hayes , Emiliano De Cristofaro

Proper communication is key to the adoption and implementation of differential privacy (DP). However, a prior study found that laypeople did not understand the data perturbation processes of DP and how DP noise protects their sensitive…

Cryptography and Security · Computer Science 2022-02-22 Aiping Xiong , Chuhao Wu , Tianhao Wang , Robert W. Proctor , Jeremiah Blocki , Ninghui Li , Somesh Jha

Recent work of Erlingsson, Feldman, Mironov, Raghunathan, Talwar, and Thakurta [EFMRTT19] demonstrates that random shuffling amplifies differential privacy guarantees of locally randomized data. Such amplification implies substantially…

Machine Learning · Computer Science 2021-09-09 Vitaly Feldman , Audra McMillan , Kunal Talwar

Differential Privacy (DP) has become the gold standard for protecting individual privacy in data analytics, and the shuffle-DP model has attracted significant attention from both academia and industry due to its favorable balance between…

Cryptography and Security · Computer Science 2026-05-04 Siyi Wang , Qiyao Luo , Yihua Hu , Lixu Wang , Quanqing Xu , Chuanhui Yang , Zhan Qin , Kui Ren , Wei Dong

Differentially private (DP) machine learning algorithms incur many sources of randomness, such as random initialization, random batch subsampling, and shuffling. However, such randomness is difficult to take into account when proving…

Machine Learning · Statistics 2023-11-02 Chendi Wang , Buxin Su , Jiayuan Ye , Reza Shokri , Weijie J. Su

We develop a sharp, experiment-level privacy theory for amplification by shuffling in the Gaussian regime: a fixed finite-output local randomizer with full support and neighboring binary datasets differing in one user. We first prove exact…

Information Theory · Computer Science 2026-03-24 Alex Shvets

We study differentially private distributed optimization under communication constraints. A server using SGD for optimization aggregates the client-side local gradients for model updates using distributed mean estimation (DME). We develop a…

Machine Learning · Computer Science 2023-02-23 Antonious M. Girgis , Suhas Diggavi

We study privacy in a distributed learning framework, where clients collaboratively build a learning model iteratively through interactions with a server from whom we need privacy. Motivated by stochastic optimization and the federated…

Machine Learning · Computer Science 2021-07-20 Antonious M. Girgis , Deepesh Data , Suhas Diggavi

Differentially private mechanisms achieving worst-case optimal error bounds (e.g., the classical Laplace mechanism) are well-studied in the literature. However, when typical data are far from the worst case, \emph{instance-specific} error…

Cryptography and Security · Computer Science 2024-09-02 Wei Dong , Qiyao Luo , Giulia Fanti , Elaine Shi , Ke Yi

Recently, it is shown that shuffling can amplify the central differential privacy guarantees of data randomized with local differential privacy. Within this setup, a centralized, trusted shuffler is responsible for shuffling by keeping the…

Cryptography and Security · Computer Science 2022-07-05 Seng Pei Liew , Tsubasa Takahashi , Shun Takagi , Fumiyuki Kato , Yang Cao , Masatoshi Yoshikawa

Recent work in differential privacy has highlighted the shuffled model as a promising avenue to compute accurate statistics while keeping raw data in users' hands. We present a protocol in this model that estimates histograms with error…

Cryptography and Security · Computer Science 2020-04-15 Victor Balcer , Albert Cheu

Reinforcement learning (RL) is a powerful tool for sequential decision-making, but its application is often hindered by privacy concerns arising from its interaction data. This challenge is particularly acute in advanced networked systems,…

Machine Learning · Computer Science 2025-11-18 Shaojie Bai , Mohammad Sadegh Talebi , Chengcheng Zhao , Peng Cheng , Jiming Chen

Deep learning draws heavily on the latest progress in semantic communications. The present paper aims to examine the security aspect of this cutting-edge technique from a novel shuffling perspective. Our goal is to improve upon the…

Cryptography and Security · Computer Science 2025-07-11 Fupei Chen , Liyao Xiang , Haoxiang Sun , Hei Victor Cheng , Kaiming Shen

We study a protocol for distributed computation called shuffled check-in, which achieves strong privacy guarantees without requiring any further trust assumptions beyond a trusted shuffler. Unlike most existing work, shuffled check-in…

Machine Learning · Computer Science 2023-07-06 Seng Pei Liew , Satoshi Hasegawa , Tsubasa Takahashi

Advances in communications, storage and computational technology allow significant quantities of data to be collected and processed by distributed devices. Combining the information from these endpoints can realize significant societal…

Cryptography and Security · Computer Science 2022-02-01 Mary Scott , Graham Cormode , Carsten Maple

Balancing utility and differential privacy by shuffling or \textit{BUDS} is an approach towards crowd-sourced, statistical databases, with strong privacy and utility balance using differential privacy theory. Here, a novel algorithm is…

Machine Learning · Computer Science 2020-06-09 Poushali Sengupta , Sudipta Paul , Subhankar Mishra

We study the setup where each of $n$ users holds an element from a discrete set, and the goal is to count the number of distinct elements across all users, under the constraint of $(\epsilon, \delta)$-differentially privacy: - In the…

Cryptography and Security · Computer Science 2020-09-22 Lijie Chen , Badih Ghazi , Ravi Kumar , Pasin Manurangsi

We study a setting of collecting and learning from private data distributed across end users. In the shuffled model of differential privacy, the end users partially protect their data locally before sharing it, and their data is also…

Machine Learning · Computer Science 2025-02-21 Tal Wagner