English
Related papers

Related papers: Privacy Amplification for BandMF via $b$-Min-Sep S…

200 papers

Privacy-preserving distributed processing has received considerable attention recently. The main purpose of these algorithms is to solve certain signal processing tasks over a network in a decentralised fashion without revealing…

Signal Processing · Electrical Eng. & Systems 2023-12-14 Sebastian O. Jordan , Qiongxiu Li , Richard Heusdens

In the literature of data privacy, differential privacy is the most popular model. An algorithm is differentially private if its outputs with and without any individual's data are indistinguishable. In this paper, we focus on data generated…

Cryptography and Security · Computer Science 2022-06-24 Darshan Chakrabarti , Jie Gao , Aditya Saraf , Grant Schoenebeck , Fang-Yi Yu

Differentially Private Stochastic Gradient Descent (DPSGD) is widely used to train deep neural networks with formal privacy guarantees. However, the addition of differential privacy (DP) often degrades model accuracy by introducing both…

Machine Learning · Computer Science 2025-11-13 Xincheng Xu , Thilina Ranbaduge , Qing Wang , Thierry Rakotoarivelo , David Smith

We study how inherent randomness in the training process -- where each sample (or client in federated learning) contributes only to a randomly selected portion of training -- can be leveraged for privacy amplification. This includes (1)…

Machine Learning · Computer Science 2025-06-03 Andy Dong , Wei-Ning Chen , Ayfer Ozgur

We consider training models with differential privacy (DP) using mini-batch gradients. The existing state-of-the-art, Differentially Private Stochastic Gradient Descent (DP-SGD), requires privacy amplification by sampling or shuffling to…

Cryptography and Security · Computer Science 2021-12-13 Peter Kairouz , Brendan McMahan , Shuang Song , Om Thakkar , Abhradeep Thakurta , Zheng Xu

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

Recent research in differential privacy demonstrated that (sub)sampling can amplify the level of protection. For example, for $\epsilon$-differential privacy and simple random sampling with sampling rate $r$, the actual privacy guarantee is…

Applications · Statistics 2022-02-22 Jingchen Hu , Joerg Drechsler , Hang J. Kim

In this work, we give a new technique for analyzing individualized privacy accounting via the following simple observation: if an algorithm is one-sided add-DP, then its subsampled variant satisfies two-sided DP. From this, we obtain…

Data Structures and Algorithms · Computer Science 2024-05-30 Badih Ghazi , Pritish Kamath , Ravi Kumar , Pasin Manurangsi , Adam Sealfon

Differential Privacy (DP) mechanisms usually {force} reduction in data utility by producing "out-of-bound" noisy results for a tight privacy budget. We introduce the Budget Recycling Differential Privacy (BR-DP) framework, designed to…

Cryptography and Security · Computer Science 2024-07-15 Bo Jiang , Jian Du , Sagar Sharma , Qiang Yan

Differential privacy schemes have been widely adopted in recent years to address issues of data privacy protection. We propose a new Gaussian scheme combining with another data protection technique, called random orthogonal matrix masking,…

Cryptography and Security · Computer Science 2023-04-13 A. Adam Ding , Samuel S. Wu , Guanhong Miao , Shigang Chen

Data-dependent privacy accounting frameworks such as per-instance differential privacy (pDP) and Fisher information loss (FIL) confer fine-grained privacy guarantees for individuals in a fixed training dataset. These guarantees can be…

Cryptography and Security · Computer Science 2024-03-12 Shengyuan Hu , Saeed Mahloujifar , Virginia Smith , Kamalika Chaudhuri , Chuan Guo

Strict privacy is of paramount importance in distributed machine learning. Federated learning, with the main idea of communicating only what is needed for learning, has been recently introduced as a general approach for distributed learning…

Cryptography and Security · Computer Science 2020-07-14 Mikko A. Heikkilä , Antti Koskela , Kana Shimizu , Samuel Kaski , Antti Honkela

This paper introduces a new method that embeds any Bayesian model used to generate synthetic data and converts it into a differentially private (DP) mechanism. We propose an alteration of the model synthesizer to utilize a censored…

Methodology · Statistics 2023-08-07 Jingchen Hu , Matthew R. Williams , Terrance D. Savitsky

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

Differential privacy (DP) is becoming increasingly important for deployed machine learning applications because it provides strong guarantees for protecting the privacy of individuals whose data is used to train models. However, DP…

Sampling is renowned for its privacy amplification in differential privacy (DP), and is often assumed to improve the utility of a DP mechanism by allowing a noise reduction. In this paper, we further show that this last assumption is…

Cryptography and Security · Computer Science 2026-01-23 Àlex Miranda-Pascual , Javier Parra-Arnau , Thorsten Strufe

Privacy is a growing concern in modern deep-learning systems and applications. Differentially private (DP) training prevents the leakage of sensitive information in the collected training data from the trained machine learning models. DP…

Machine Learning · Computer Science 2024-08-28 Xinwei Zhang , Zhiqi Bu , Mingyi Hong , Meisam Razaviyayn

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

Posterior sampling, i.e., exponential mechanism to sample from the posterior distribution, provides $\varepsilon$-pure differential privacy (DP) guarantees and does not suffer from potentially unbounded privacy breach introduced by…

Machine Learning · Computer Science 2024-05-02 Yingyu Lin , Yi-An Ma , Yu-Xiang Wang , Rachel Redberg , Zhiqi Bu

Differentially private stochastic gradient descent (DP-SGD) is a standard approach to privacy-preserving learning based on per-example clipping, subsampling, Gaussian perturbation, and privacy accounting. Classical DP-SGD releases a noisy…

Cryptography and Security · Computer Science 2026-05-12 Mohammad Partohaghighi , Roummel Marcia