English
Related papers

Related papers: Privacy amplification and decoupling without smoot…

200 papers

We characterize the minimum noise amplitude and power for noise-adding mechanisms in $(\epsilon, \delta)$-differential privacy for single real-valued query function. We derive new lower bounds using the duality of linear programming, and…

Cryptography and Security · Computer Science 2019-02-06 Quan Geng , Wei Ding , Ruiqi Guo , Sanjiv Kumar

Differential privacy (DP) is the de facto standard for private data release and private machine learning. Auditing black-box DP algorithms and mechanisms to certify whether they satisfy a certain DP guarantee is challenging, especially in…

Machine Learning · Computer Science 2022-05-30 Carles Domingo-Enrich , Youssef Mroueh

This thesis consolidates, improves and extends the smooth entropy framework for non-asymptotic information theory and cryptography. We investigate the conditional min- and max-entropy for quantum states, generalizations of classical R\'enyi…

Quantum Physics · Physics 2015-03-20 Marco Tomamichel

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

Quantum information decoupling is a fundamental primitive in quantum information theory, underlying various applications in quantum physics. We prove a novel one-shot decoupling theorem formulated in terms of quantum relative entropy…

Quantum Physics · Physics 2026-02-20 Mario Berta , Hao-Chung Cheng , Yongsheng Yao

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

We introduce a set of useful expressions of Differential Privacy (DP) notions in terms of the Laplace transform of the privacy loss distribution. Its bare form expression appears in several related works on analyzing DP, either as an…

Machine Learning · Computer Science 2024-11-15 Rishav Chourasia , Uzair Javaid , Biplap Sikdar

Privacy amplification is the key step to guarantee the security of quantum communication. The existing security proofs require accumulating a large number of raw key bits for privacy amplification. This is similar to block ciphers in…

Quantum Physics · Physics 2022-07-05 Yizhi Huang , Xingjian Zhang , Xiongfeng Ma

Zeroth-order optimization has emerged as a promising approach for fine-tuning large language models under differential privacy (DP) and memory constraints. While privacy amplification by iteration (PABI) provides convergent DP bounds for…

Machine Learning · Computer Science 2026-05-15 Eli Chien , Wei-Ning Chen , Pan Li

Pufferfish privacy is a flexible generalization of differential privacy that allows to model arbitrary secrets and adversary's prior knowledge about the data. Unfortunately, designing general and tractable Pufferfish mechanisms that do not…

Cryptography and Security · Computer Science 2024-06-11 Clément Pierquin , Aurélien Bellet , Marc Tommasi , Matthieu Boussard

R\'enyi entropies are conceptually valuable and experimentally relevant generalisations of the celebrated von Neumann entanglement entropy. After a quantum quench in a clean quantum many-body system they generically display a universal…

Statistical Mechanics · Physics 2022-08-04 Bruno Bertini , Katja Klobas , Vincenzo Alba , Gianluca Lagnese , Pasquale Calabrese

In this paper, we consider the framework of privacy amplification via iteration, which is originally proposed by Feldman et al. and subsequently simplified by Asoodeh et al. in their analysis via the contraction coefficient. This line of…

Cryptography and Security · Computer Science 2021-06-23 Matteo Sordello , Zhiqi Bu , Jinshuo Dong

In this article we deal with the security of the BB84 quantum cryptography protocol over noisy channels using generalized privacy amplification. For this we estimate the fraction of bits needed to be discarded during the privacy…

Quantum Physics · Physics 2007-05-23 N. Lütkenhaus , Stephen M. Barnett

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

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

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 investigate the scaling of the R\'enyi $\alpha$-entropies in one-dimensional gapped quantum spin models. We show that the block entropies with $\alpha > 2$ violate the area law monotonicity and exhibit damped oscillations. Depending on…

Strongly Correlated Electrons · Physics 2012-08-06 S. M. Giampaolo , S. Montangero , F. Dell'Anno , S. De Siena , F. Illuminati

Differential privacy is a useful tool to build machine learning models which do not release too much information about the training data. We study the R\'enyi differential privacy of stochastic gradient descent when each training example is…

Machine Learning · Computer Science 2020-02-18 Eloïse Berthier , Sai Praneeth Karimireddy

In many systems privacy of users depends on the number of participants applying collectively some method to protect their security. Indeed, there are numerous already classic results about revealing aggregated data from a set of users. The…

Social and Information Networks · Computer Science 2017-04-27 Krzysztof Grining , Marek Klonowski , Małgorzata Sulkowska

This work explores properties of Strong Data-Processing constants for R\'enyi Divergences. Parallels are made with the well-studied $\varphi$-Divergences, and it is shown that the order $\alpha$ of R\'enyi Divergences dictates whether…

Information Theory · Computer Science 2026-01-15 Adrien Vandenbroucque , Amedeo Roberto Esposito , Michael Gastpar