English
Related papers

Related papers: Privacy Amplification Via Bernoulli Sampling

200 papers

This chapter is meant to be part of the book "Differential Privacy for Artificial Intelligence Applications." We give an introduction to the most important property of differential privacy -- composition: running multiple independent…

Cryptography and Security · Computer Science 2022-10-27 Thomas Steinke

We study the privacy risks that are associated with training a neural network's weights with self-supervised learning algorithms. Through empirical evidence, we show that the fine-tuning stage, in which the network weights are updated with…

Machine Learning · Computer Science 2022-05-26 Yunhao Yang , Parham Gohari , Ufuk Topcu

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

The shuffle model of Differential Privacy (DP) has gained significant attention in privacy-preserving data analysis due to its remarkable tradeoff between privacy and utility. It is characterized by adding a shuffling procedure after each…

Combinatorics · Mathematics 2024-01-10 E Chen , Yang Cao , Yifei Ge

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…

Information Theory · Computer Science 2017-03-08 Jianping He , Lin Cai

Privacy amplification is an indispensable step in the post-processing of quantum key distribution, which can be used to compress the redundancy of shared key and improve the security level of the key. The commonly used privacy amplification…

Quantum Physics · Physics 2021-09-16 Wei Li , Shengmei Zhao

Aggregate time-series data like traffic flow and site occupancy repeatedly sample statistics from a population across time. Such data can be profoundly useful for understanding trends within a given population, but also pose a significant…

Cryptography and Security · Computer Science 2022-01-14 Tatsuki Koga , Casey Meehan , Kamalika Chaudhuri

We study how to communicate findings of Bayesian inference to third parties, while preserving the strong guarantee of differential privacy. Our main contributions are four different algorithms for private Bayesian inference on…

Artificial Intelligence · Computer Science 2015-12-23 Zuhe Zhang , Benjamin Rubinstein , Christos Dimitrakakis

Large data collections required for the training of neural networks often contain sensitive information such as the medical histories of patients, and the privacy of the training data must be preserved. In this paper, we introduce a dropout…

Machine Learning · Statistics 2017-12-06 Beyza Ermis , Ali Taylan Cemgil

The shuffle model of differential privacy provides promising privacy-utility balances in decentralized, privacy-preserving data analysis. However, the current analyses of privacy amplification via shuffling lack both tightness and…

Cryptography and Security · Computer Science 2024-07-30 Shaowei Wang , Yun Peng , Jin Li , Zikai Wen , Zhipeng Li , Shiyu Yu , Di Wang , Wei Yang

Differential Privacy (DP) is a probabilistic framework that protects privacy while preserving data utility. To protect the privacy of the individuals in the dataset, DP requires adding a precise amount of noise to a statistic of interest;…

Computation · Statistics 2025-05-05 Yu-Wei Chen , Pranav Sanghi , Jordan Awan

Many forms of sensitive data, such as web traffic, mobility data, or hospital occupancy, are inherently sequential. The standard method for training machine learning models while ensuring privacy for units of sensitive information, such as…

We study privacy amplification for differentially private model training with matrix factorization under random allocation (also known as the balls-in-bins model). Recent work by Choquette-Choo et al. (2025) proposes a sampling-based Monte…

Machine Learning · Computer Science 2026-05-18 Jan Schuchardt , Nikita Kalinin

Poisson subsampling is the default sampling scheme in differentially private machine learning, largely because its unstructured randomness yields tractable privacy amplification analyses. Yet this same randomness introduces substantial…

Machine Learning · Computer Science 2026-05-11 Andy Dong , Ayfer Özgür

Privacy preservation is a fundamental requirement in many high-stakes domains such as medicine and finance, where sensitive personal data must be analyzed without compromising individual confidentiality. At the same time, these applications…

Machine Learning · Statistics 2026-02-05 Simon Roburin , Rafaël Pinot , Erwan Scornet

Many resource allocation problems can be formulated as an optimization problem whose constraints contain sensitive information about participating users. This paper concerns solving this kind of optimization problem in a distributed manner…

Optimization and Control · Mathematics 2016-11-17 Shuo Han , Ufuk Topcu , George J. Pappas

The exponential increase in the amount of available data makes taking advantage of them without violating users' privacy one of the fundamental problems of computer science. This question has been investigated thoroughly under the framework…

Data Structures and Algorithms · Computer Science 2023-07-19 Jakub Tětek

The shuffle model of differential privacy has gained significant interest as an intermediate trust model between the standard local and central models [EFMRTT19; CSUZZ19]. A key result in this model is that randomly shuffling locally…

Cryptography and Security · Computer Science 2023-11-01 Vitaly Feldman , Audra McMillan , Kunal Talwar

Differential privacy is a leading protection setting, focused by design on individual privacy. Many applications, in medical / pharmaceutical domains or social networks, rather posit privacy at a group level, a setting we call integral…

Machine Learning · Statistics 2019-07-04 Hisham Husain , Zac Cranko , Richard Nock

Bayesian optimization is a powerful tool for fine-tuning the hyper-parameters of a wide variety of machine learning models. The success of machine learning has led practitioners in diverse real-world settings to learn classifiers for…

Machine Learning · Statistics 2015-02-24 Matt J. Kusner , Jacob R. Gardner , Roman Garnett , Kilian Q. Weinberger