English
Related papers

Related papers: Privacy for Free: Posterior Sampling and Stochasti…

200 papers

Differentially Private Stochastic Gradient Descent (DP-SGD) is a key method for applying privacy in the training of deep learning models. It applies isotropic Gaussian noise to gradients during training, which can perturb these gradients in…

Machine Learning · Computer Science 2023-11-28 Pedro Faustini , Natasha Fernandes , Shakila Tonni , Annabelle McIver , Mark Dras

Differentially private collaborative filtering is a challenging task, both in terms of accuracy and speed. We present a simple algorithm that is provably differentially private, while offering good performance, using a novel connection of…

Machine Learning · Computer Science 2015-05-08 Ziqi Liu , Yu-Xiang Wang , Alexander J. Smola

Although theoretically compelling, Bayesian learning with modern machine learning models is computationally challenging since it requires approximating a high dimensional posterior distribution. In this work, we (i) introduce posteriors, an…

Machine Learning · Computer Science 2025-04-15 Samuel Duffield , Kaelan Donatella , Johnathan Chiu , Phoebe Klett , Daniel Simpson

The worldwide adoption of machine learning (ML) and deep learning models, particularly in critical sectors, such as healthcare and finance, presents substantial challenges in maintaining individual privacy and fairness. These two elements…

Machine Learning · Computer Science 2024-04-16 Mengmeng Yang , Ming Ding , Youyang Qu , Wei Ni , David Smith , Thierry Rakotoarivelo

Privacy preserving mechanisms such as differential privacy inject additional randomness in the form of noise in the data, beyond the sampling mechanism. Ignoring this additional noise can lead to inaccurate and invalid inferences. In this…

Machine Learning · Statistics 2015-11-26 Vishesh Karwa , Dan Kifer , Aleksandra B. Slavković

In this paper we present the Sampling Privacy mechanism for privately releasing personal data. Sampling Privacy is a sampling based privacy mechanism that satisfies differential privacy.

Cryptography and Security · Computer Science 2017-08-08 Josh Joy , Mario Gerla

It is challenging for stochastic optimizations to handle large-scale sensitive data safely. Recently, Duchi et al. proposed private sampling strategy to solve privacy leakage in stochastic optimizations. However, this strategy leads to…

Cryptography and Security · Computer Science 2018-10-02 Bo Han , Ivor W. Tsang , Xiaokui Xiao , Ling Chen , Sai-fu Fung , Celina P. Yu

In several practical applications of federated learning (FL), the clients are highly heterogeneous in terms of both their data and compute resources, and therefore enforcing the same model architecture for each client is very limiting.…

Machine Learning · Computer Science 2023-06-14 Disha Makhija , Joydeep Ghosh , Nhat Ho

Differential privacy (DP) has become the de facto standard of privacy preservation due to its strong protection and sound mathematical foundation, which is widely adopted in different applications such as big data analysis, graph data…

Cryptography and Security · Computer Science 2021-12-06 Honglu Jiang , Yifeng Gao , S M Sarwar , Luis GarzaPerez , Mahmudul Robin

This paper discusses how two classes of approximate computation algorithms can be adapted, in a modular fashion, to achieve exact statistical inference from differentially private data products. Considered are approximate Bayesian…

Computation · Statistics 2022-09-28 Ruobin Gong

Distributed stochastic gradient descent is an important subroutine in distributed learning. A setting of particular interest is when the clients are mobile devices, where two important concerns are communication efficiency and the privacy…

Machine Learning · Statistics 2018-05-29 Naman Agarwal , Ananda Theertha Suresh , Felix Yu , Sanjiv Kumar , H. Brendan Mcmahan

Recently, there has been a number of papers relating mechanism design and privacy (e.g., see \cite{MT07,Xia11,CCKMV11,NST12,NOS12,HK12}). All of these papers consider a worst-case setting where there is no probabilistic information about…

Computer Science and Game Theory · Computer Science 2014-11-25 Samantha Leung , Edward Lui

In machine learning, classification models need to be trained in order to predict class labels. When the training data contains personal information about individuals, collecting training data becomes difficult due to privacy concerns.…

Machine Learning · Computer Science 2019-05-06 Emre Yilmaz , Mohammad Al-Rubaie , J. Morris Chang

Differential privacy is a mathematical concept that provides an information-theoretic security guarantee. While differential privacy has emerged as a de facto standard for guaranteeing privacy in data sharing, the known mechanisms to…

Cryptography and Security · Computer Science 2024-03-26 March Boedihardjo , Thomas Strohmer , Roman Vershynin

While modern machine learning models rely on increasingly large training datasets, data is often limited in privacy-sensitive domains. Generative models trained with differential privacy (DP) on sensitive data can sidestep this challenge,…

Machine Learning · Statistics 2024-01-02 Tim Dockhorn , Tianshi Cao , Arash Vahdat , Karsten Kreis

In order to both learn and protect sensitive training data, there has been a growing interest in privacy preserving machine learning methods. Differential privacy has emerged as an important measure of privacy. We are interested in the…

Cryptography and Security · Computer Science 2025-02-11 Antoine Barczewski , Amal Mawass , Jan Ramon

Monte Carlo sampling techniques have broad applications in machine learning, Bayesian posterior inference, and parameter estimation. Often the target distribution takes the form of a product distribution over a dataset with a large number…

Methodology · Statistics 2019-09-19 Charles Matthews , Jonathan Weare

This paper aims to provide differential privacy (DP) guarantees for Markov chain Monte Carlo (MCMC) algorithms. In a first part, we establish DP guarantees on samples output by MCMC algorithms as well as Monte Carlo estimators associated…

Machine Learning · Statistics 2025-11-04 Andrea Bertazzi , Tim Johnston , Gareth O. Roberts , Alain Durmus

We study private prediction where differential privacy is achieved by adding noise to the outputs of a non-private model. Existing methods rely on noise proportional to the global sensitivity of the model, often resulting in sub-optimal…

Machine learning techniques based on neural networks are achieving remarkable results in a wide variety of domains. Often, the training of models requires large, representative datasets, which may be crowdsourced and contain sensitive…

Machine Learning · Statistics 2018-12-21 Martín Abadi , Andy Chu , Ian Goodfellow , H. Brendan McMahan , Ilya Mironov , Kunal Talwar , Li Zhang