English
Related papers

Related papers: Sharp Composition Bounds for Gaussian Differential…

200 papers

We investigate the framework of privacy amplification by iteration, recently proposed by Feldman et al., from an information-theoretic lens. We demonstrate that differential privacy guarantees of iterative mappings can be determined by a…

Information Theory · Computer Science 2020-01-22 Shahab Asoodeh , Mario Diaz , Flavio P. Calmon

The Gaussian mechanism is one differential privacy mechanism commonly used to protect numerical data. However, it may be ill-suited to some applications because it has unbounded support and thus can produce invalid numerical answers to…

Cryptography and Security · Computer Science 2022-12-01 Bo Chen , Matthew Hale

Differential privacy is a mathematical framework for developing statistical computations with provable guarantees of privacy and accuracy. In contrast to the privacy component of differential privacy, which has a clear mathematical and…

Cryptography and Security · Computer Science 2020-11-13 Gilles Barthe , Rohit Chadha , Paul Krogmeier , A. Prasad Sistla , Mahesh Viswanathan

The randomized power method has gained significant interest due to its simplicity and efficient handling of large-scale spectral analysis and recommendation tasks. However, its application to large datasets containing personal information…

Machine Learning · Computer Science 2025-06-13 Julien Nicolas , César Sabater , Mohamed Maouche , Sonia Ben Mokhtar , Mark Coates

The framework of differential privacy protects an individual's privacy while publishing query responses on congregated data. In this work, a new noise addition mechanism for differential privacy is introduced where the noise added is…

Cryptography and Security · Computer Science 2023-07-06 Gokularam Muthukrishnan , Sheetal Kalyani

Differential privacy (DP) is a widely used notion for reasoning about privacy when publishing aggregate data. In this paper, we observe that certain DP mechanisms are amenable to a posteriori privacy analysis that exploits the fact that…

Cryptography and Security · Computer Science 2023-06-21 Valentin Hartmann , Vincent Bindschaedler , Alexander Bentkamp , Robert West

The exact composition of mechanisms for which two differential privacy (DP) constraints hold simultaneously is studied. The resulting privacy region admits an exact representation as a mixture over compositions of mechanisms of…

Information Theory · Computer Science 2026-04-16 Cemre Cadir , Salim Najib , Yanina Y. Shkel

Differential Privacy (DP) considers a scenario in which an adversary has almost complete information about the entries of a database. This worst-case assumption is likely to overestimate the privacy threat faced by an individual in…

Cryptography and Security · Computer Science 2026-02-11 Dennis Breutigam , Rüdiger Reischuk

While differential privacy and gradient compression are separately well-researched topics in machine learning, the study of interaction between these two topics is still relatively new. We perform a detailed empirical study on how the…

Machine Learning · Computer Science 2022-11-03 Jimmy Lin

Differentially private (DP) mechanisms face the challenge of providing accurate results while protecting their inputs: the privacy-utility trade-off. A simple but powerful technique for DP adds noise to sensitivity-bounded query outputs to…

Cryptography and Security · Computer Science 2021-07-28 David M. Sommer , Lukas Abfalterer , Sheila Zingg , Esfandiar Mohammadi

Composition theorems are general and powerful tools that facilitate privacy accounting across multiple data accesses from per-access privacy bounds. However they often result in weaker bounds compared with end-to-end analysis. Two popular…

Cryptography and Security · Computer Science 2023-02-13 Edith Cohen , Xin Lyu , Jelani Nelson , Tamás Sarlós , Uri Stemmer

We consider training models on private data that are distributed across user devices. To ensure privacy, we add on-device noise and use secure aggregation so that only the noisy sum is revealed to the server. We present a comprehensive…

Machine Learning · Computer Science 2022-09-12 Peter Kairouz , Ziyu Liu , Thomas Steinke

A major challenge for machine learning is increasing the availability of data while respecting the privacy of individuals. Here we combine the provable privacy guarantees of the differential privacy framework with the flexibility of…

Machine Learning · Statistics 2019-01-18 Michael Thomas Smith , Max Zwiessele , Neil D. Lawrence

The Sampled Gaussian Mechanism (SGM)---a composition of subsampling and the additive Gaussian noise---has been successfully used in a number of machine learning applications. The mechanism's unexpected power is derived from privacy…

Machine Learning · Computer Science 2019-08-29 Ilya Mironov , Kunal Talwar , Li Zhang

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

With the growing volume of data in society, the need for privacy protection in data analysis also rises. In particular, private selection tasks, wherein the most important information is retrieved under differential privacy are emphasized…

Data Structures and Algorithms · Computer Science 2024-10-15 Akito Yamamoto , Tetsuo Shibuya

Motivated by the rapid rise in statistical tools in Functional Data Analysis, we consider the Gaussian mechanism for achieving differential privacy with parameter estimates taking values in a, potentially infinite-dimensional, separable…

Statistics Theory · Mathematics 2019-01-29 Ardalan Mirshani , Matthew Reimherr , Aleksandra Slavkovic

Differential privacy is increasingly formalized through the lens of hypothesis testing via the robust and interpretable $f$-DP framework, where privacy guarantees are encoded by a baseline Blackwell trade-off function $f_{\infty} =…

Statistics Theory · Mathematics 2025-12-02 Aaradhya Pandey , Arian Maleki , Sanjeev Kulkarni

Gradient perturbation, widely used for differentially private optimization, injects noise at every iterative update to guarantee differential privacy. Previous work first determines the noise level that can satisfy the privacy requirement…

Machine Learning · Computer Science 2020-10-27 Da Yu , Huishuai Zhang , Wei Chen , Tie-Yan Liu , Jian Yin

Differentially Private Stochastic Gradient Descent (DPSGD) is widely used to protect sensitive data during the training of machine learning models, but its privacy guarantee often comes at a large cost of model performance due to the lack…

Machine Learning · Computer Science 2026-01-16 Hao Liang , Wanrong Zhang , Xinlei He , Kaishun Wu , Hong Xing