English
Related papers

Related papers: Decomposition-Based Optimal Bounds for Privacy Amp…

200 papers

In privacy-preserving machine learning, individual parties are reluctant to share their sensitive training data due to privacy concerns. Even the trained model parameters or prediction can pose serious privacy leakage. To address these…

Cryptography and Security · Computer Science 2020-09-04 Lingjuan Lyu , Yee Wei Law , Kee Siong Ng , Shibei Xue , Jun Zhao , Mengmeng Yang , Lei Liu

In federated learning (FL), balancing privacy protection, learning quality, and efficiency remains a challenge. Privacy protection mechanisms, such as Differential Privacy (DP), degrade learning quality, or, as in the case of Homomorphic…

Machine Learning · Computer Science 2026-03-06 Yenan Wang , Carla Fabiana Chiasserini , Elad Michael Schiller

Composition is one of the most important properties of differential privacy (DP), as it allows algorithm designers to build complex private algorithms from DP primitives. We consider precise composition bounds of the overall privacy loss…

Cryptography and Security · Computer Science 2020-06-26 Jinshuo Dong , David Durfee , Ryan Rogers

As network data has become increasingly prevalent, a substantial amount of attention has been paid to the privacy issue in publishing network data. One of the critical challenges for data publishers is to preserve the topological structures…

Methodology · Statistics 2024-06-24 Yaoming Zhen , Shirong Xu , Junhui Wang

With decentralized optimization having increased applications in various domains ranging from machine learning, control, sensor networks, to robotics, its privacy is also receiving increased attention. Existing privacy-preserving approaches…

Optimization and Control · Mathematics 2022-07-13 Huan Gao , Yongqiang Wang , Angelia Nedić

Privacy-preserving data release algorithms have gained increasing attention for their ability to protect user privacy while enabling downstream machine learning tasks. However, the utility of current popular algorithms is not always…

Machine Learning · Computer Science 2023-12-06 Donghao Li , Yang Cao , Yuan Yao

We study the problem of discrete distribution estimation under utility-optimized local differential privacy (ULDP), which enforces local differential privacy (LDP) on sensitive data while allowing more accurate inference on non-sensitive…

Cryptography and Security · Computer Science 2025-09-30 Sun-Moon Yoon , Hyun-Young Park , Seung-Hyun Nam , Si-Hyeon Lee

We show that the `optimal' use of the parallel composition theorem corresponds to finding the size of the largest subset of queries that `overlap' on the data domain, a quantity we call the \emph{maximum overlap} of the queries. It has…

Cryptography and Security · Computer Science 2021-09-21 Josh Smith , Hassan Jameel Asghar , Gianpaolo Gioiosa , Sirine Mrabet , Serge Gaspers , Paul Tyler

Preference-based fine-tuning has become an important component in training large language models, and the data used at this stage may contain sensitive user information. A central question is how to design a differentially private pipeline…

Machine Learning · Statistics 2026-03-25 Young Hyun Cho , Will Wei Sun

Fingerprinting arguments, first introduced by Bun, Ullman, and Vadhan (STOC 2014), are the most widely used method for establishing lower bounds on the sample complexity or error of approximately differentially private (DP) algorithms.…

Cryptography and Security · Computer Science 2024-07-08 Naty Peter , Eliad Tsfadia , Jonathan Ullman

As data-driven technologies advance swiftly, maintaining strong privacy measures becomes progressively difficult. Conventional $(\epsilon, \delta)$-differential privacy, while prevalent, exhibits limited adaptability for many applications.…

Cryptography and Security · Computer Science 2025-07-03 Yifeng Liu , Zehua Wang

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 amplification by synthetic data release, a phenomenon in which differential privacy guarantees are improved by releasing only synthetic data rather than the private generative model itself. Recent work by Pierquin et al.…

Cryptography and Security · Computer Science 2026-02-06 Clément Pierquin , Aurélien Bellet , Marc Tommasi , Matthieu Boussard

The central question studied in this paper is Renyi Differential Privacy (RDP) guarantees for general discrete local mechanisms in the shuffle privacy model. In the shuffle model, each of the $n$ clients randomizes its response using a…

Cryptography and Security · Computer Science 2021-05-12 Antonious M. Girgis , Deepesh Data , Suhas Diggavi , Ananda Theertha Suresh , Peter Kairouz

Fine-tuning large pre-trained foundation models (FMs) on distributed edge devices presents considerable computational and privacy challenges. Federated fine-tuning (FedFT) mitigates some privacy issues by facilitating collaborative model…

Machine Learning · Computer Science 2024-11-28 Tianqu Kang , Zixin Wang , Hengtao He , Jun Zhang , Shenghui Song , Khaled B. Letaief

We examine the privacy amplification of channels that do not necessarily satisfy any LDP guarantee by analyzing their contraction behavior in terms of $f_\alpha$-divergence, an $f$-divergence related to R\'enyi-divergence via a monotonic…

Information Theory · Computer Science 2025-11-27 Leonhard Grosse , Sara Saeidian , Tobias J. Oechtering , Mikael Skoglund

In this paper, we develop compositional methods for formally verifying differential privacy for algorithms whose analysis goes beyond the composition theorem. Our methods are based on the observation that differential privacy has deep…

Logic in Computer Science · Computer Science 2021-03-16 Gilles Barthe , Marco Gaboardi , Benjamin Grégoire , Justin Hsu , Pierre-Yves Strub

In this paper, we propose a novel learnable image encryption method for privacy-preserving deep neural networks (DNNs). The proposed method is carried out on the basis of block scrambling used in combination with data augmentation…

Cryptography and Security · Computer Science 2021-06-01 Tatsuya Chuman , Hitoshi Kiya

We present the notion of \emph{reasonable utility} for binary mechanisms, which applies to all utility functions in the literature. This notion induces a partial ordering on the performance of all binary differentially private (DP)…

Information Theory · Computer Science 2023-11-01 Sahel Torkamani , Javad B. Ebrahimi , Parastoo Sadeghi , Rafael G. L. D'Oliveira , Muriel Médard

Many commonly used learning algorithms work by iteratively updating an intermediate solution using one or a few data points in each iteration. Analysis of differential privacy for such algorithms often involves ensuring privacy of each step…

Machine Learning · Computer Science 2018-12-12 Vitaly Feldman , Ilya Mironov , Kunal Talwar , Abhradeep Thakurta