English
Related papers

Related papers: Subsampled R\'enyi Differential Privacy and Analyt…

200 papers

Using a recently proposed privacy definition of R\'enyi Differential Privacy (RDP), we re-examine the inherent privacy of releasing a single sample from a posterior distribution. We exploit the impact of the prior distribution in mitigating…

Machine Learning · Computer Science 2017-10-04 Joseph Geumlek , Shuang Song , Kamalika Chaudhuri

We study Gaussian mechanism in the shuffle model of differential privacy (DP). Particularly, we characterize the mechanism's R\'enyi differential privacy (RDP), showing that it is of the form: $$ \epsilon(\lambda) \leq…

Cryptography and Security · Computer Science 2023-07-05 Seng Pei Liew , Tsubasa Takahashi

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

Individual privacy accounting enables bounding differential privacy (DP) loss individually for each participant involved in the analysis. This can be informative as often the individual privacy losses are considerably smaller than those…

Cryptography and Security · Computer Science 2023-08-25 Antti Koskela , Marlon Tobaben , Antti Honkela

Amplification by subsampling is one of the main primitives in machine learning with differential privacy (DP): Training a model on random batches instead of complete datasets results in stronger privacy. This is traditionally formalized via…

Cryptography and Security · Computer Science 2024-11-04 Jan Schuchardt , Mihail Stoian , Arthur Kosmala , Stephan Günnemann

We consider three different variants of differential privacy (DP), namely approximate DP, R\'enyi DP (RDP), and hypothesis test DP. In the first part, we develop a machinery for optimally relating approximate DP to RDP based on the joint…

Information Theory · Computer Science 2021-01-26 Shahab Asoodeh , Jiachun Liao , Flavio P. Calmon , Oliver Kosut , Lalitha Sankar

Private selection mechanisms (e.g., Report Noisy Max, Sparse Vector) are fundamental primitives of differentially private (DP) data analysis with wide applications to private query release, voting, and hyperparameter tuning. Recent work…

Cryptography and Security · Computer Science 2024-02-13 Antti Koskela , Rachel Redberg , Yu-Xiang Wang

We study privacy in a distributed learning framework, where clients collaboratively build a learning model iteratively through interactions with a server from whom we need privacy. Motivated by stochastic optimization and the federated…

Machine Learning · Computer Science 2021-07-20 Antonious M. Girgis , Deepesh Data , Suhas Diggavi

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

We derive the optimal differential privacy (DP) parameters of a mechanism that satisfies a given level of R\'enyi differential privacy (RDP). Our result is based on the joint range of two $f$-divergences that underlie the approximate and…

Information Theory · Computer Science 2020-01-17 Shahab Asoodeh , Jiachun Liao , Flavio P. Calmon , Oliver Kosut , Lalitha Sankar

We consider the privacy amplification properties of a sampling scheme in which a user's data is used in $k$ steps chosen randomly and uniformly from a sequence (or set) of $t$ steps. This sampling scheme has been recently applied in the…

Machine Learning · Computer Science 2026-02-20 Vitaly Feldman , Moshe Shenfeld

Tuning the hyperparameters of differentially private (DP) machine learning (ML) algorithms often requires use of sensitive data and this may leak private information via hyperparameter values. Recently, Papernot and Steinke (2022) proposed…

Machine Learning · Computer Science 2024-02-14 Antti Koskela , Tejas Kulkarni

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

Personalized privacy becomes critical in deep learning for Trustworthy AI. While Differentially Private Stochastic Gradient Descent (DP-SGD) is widely used in deep learning methods supporting privacy, it provides the same level of privacy…

Machine Learning · Computer Science 2023-05-25 Geon Heo , Junseok Seo , Steven Euijong Whang

Differential Privacy (DP) is the leading approach to privacy preserving deep learning. As such, there are multiple efforts to provide drop-in integration of DP into popular frameworks. These efforts, which add noise to each gradient…

Machine Learning · Statistics 2021-06-08 Mathias Lécuyer

Designing privacy-preserving machine learning algorithms has received great attention in recent years, especially in the setting when the data contains sensitive information. Differential privacy (DP) is a widely used mechanism for data…

Machine Learning · Computer Science 2025-09-11 Chunyang Liao , Deanna Needell , Hayden Schaeffer , Alexander Xue

We consider the problem of computing tight privacy guarantees for the composition of subsampled differentially private mechanisms. Recent algorithms can numerically compute the privacy parameters to arbitrary precision but must be carefully…

Cryptography and Security · Computer Science 2025-04-09 Christian Janos Lebeda , Matthew Regehr , Gautam Kamath , Thomas Steinke

Gaussian sketching, which consists of pre-multiplying the data with a random Gaussian matrix, is a widely used technique for multiple problems in data science and machine learning, with applications spanning computationally efficient…

Machine Learning · Computer Science 2025-06-05 Omri Lev , Vishwak Srinivasan , Moshe Shenfeld , Katrina Ligett , Ayush Sekhari , Ashia C. Wilson

Prior work on differential privacy analysis of randomized SGD algorithms relies on composition theorems, where the implicit (unrealistic) assumption is that the internal state of the iterative algorithm is revealed to the adversary. As a…

Machine Learning · Statistics 2022-10-18 Jiayuan Ye , Reza Shokri

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
‹ Prev 1 2 3 10 Next ›