English
Related papers

Related papers: Outer Bounds on the CEO Problem with Privacy Const…

200 papers

We investigate the upper and lower bounds on the quantization distortions for independent and identically distributed sources in the finite block-length regime. Based on the convex optimization framework of the rate-distortion theory, we…

Information Theory · Computer Science 2013-06-21 Chen Gong , Xiaodong Wang

The problem of preserving the privacy of individual entries of a database when responding to linear or nonlinear queries with constrained additive noise is considered. For privacy protection, the response to the query is systematically…

Optimization and Control · Mathematics 2018-08-30 Farhad Farokhi , Henrik Sandberg

We study a statistical signal processing privacy problem, where an agent observes useful data $Y$ and wants to reveal the information to a user. Since the useful data is correlated with the private data $X$, the agent employs a privacy…

Information Theory · Computer Science 2021-07-16 Amirreza Zamani , Tobias J. Oechtering , Mikael Skoglund

The secrecy capacity of relay channels with orthogonal components is studied in the presence of an additional passive eavesdropper node. The relay and destination receive signals from the source on two orthogonal channels such that the…

Information Theory · Computer Science 2009-06-09 Vaneet Aggarwal , Lalitha Sankar , A. Robert Calderbank , H. Vincent Poor

Differential privacy (DP) has been applied in deep learning for preserving privacy of the underlying training sets. Existing DP practice falls into three categories - objective perturbation, gradient perturbation and output perturbation.…

Cryptography and Security · Computer Science 2022-04-28 Zhigang Lu , Hassan Jameel Asghar , Mohamed Ali Kaafar , Darren Webb , Peter Dickinson

An undetected eavesdropping attack must produce count rate statistics that are indistinguishable from those that would arise in the absence of such an attack. In principle this constraint should force a reduction in the amount of…

Quantum Physics · Physics 2007-05-23 G. Gilbert , M. Hamrick

We show that a large fraction of the data-structure lower bounds known today in fact follow by reduction from the communication complexity of lopsided (asymmetric) set disjointness. This includes lower bounds for: * high-dimensional…

Data Structures and Algorithms · Computer Science 2010-10-20 Mihai Patrascu

We approach index coding as a special case of rate-distortion with multiple receivers, each with some side information about the source. Specifically, using techniques developed for the rate-distortion problem, we provide two upper bounds…

Information Theory · Computer Science 2015-07-28 Sinem Unal , Aaron B. Wagner

In this paper, we propose an efficient coding scheme for the two-link binary Chief Executive Officer (CEO) problem under logarithmic loss criterion. The exact rate-distortion bound for a two-link binary CEO problem under the logarithmic…

Information Theory · Computer Science 2018-01-10 Mahdi Nangir , Reza Asvadi , Mahmoud Ahmadian-Attari , Jun Chen

A lossy source coding problem is studied in which a source encoder communicates with two decoders, one with and one without correlated side information with an additional constraint on the privacy of the side information at the uninformed…

Information Theory · Computer Science 2011-06-13 Ravi Tandon , Lalitha Sankar , H. Vincent Poor

We consider secure multi-terminal source coding problems in the presence of a public helper. Two main scenarios are studied: 1) source coding with a helper where the coded side information from the helper is eavesdropped by an external…

Information Theory · Computer Science 2013-07-05 Kittipong Kittichokechai , Yeow-Khiang Chia , Tobias J. Oechtering , Mikael Skoglund , Tsachy Weissman

We consider the communication scenario where a source-destination pair wishes to keep the information secret from a relay node despite wanting to enlist its help. For this scenario, an interesting question is whether the relay node should…

Information Theory · Computer Science 2016-11-15 Xiang He , Aylin Yener

A comparison between the joint and the successive decoding schemes for a two-link case binary Chief Executive Officer (CEO) problem is presented. We utilize the logarithmic loss as the criterion for measuring and comparing the total…

Information Theory · Computer Science 2020-04-14 Mahdi Nangir , Jafar Pourrostam , Javad Musevi Niya , Behzad Mozaffari Tazehkand

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

We consider the problem of privacy-preserving data release for a specific utility task under perfect obfuscation constraint. We establish the necessary and sufficient condition to extract features of the original data that carry as much…

Information Theory · Computer Science 2020-09-10 Behrooz Razeghi , Flavio. P. Calmon , Deniz Gunduz , Slava Voloshynovskiy

Differential Privacy (DP) provides an elegant mathematical framework for defining a provable disclosure risk in the presence of arbitrary adversaries; it guarantees that whether an individual is in a database or not, the results of a DP…

Cryptography and Security · Computer Science 2021-08-19 Aleksandra Slavkovic , Roberto Molinari

We study online change point detection problems under the constraint of local differential privacy (LDP) where, in particular, the statistician does not have access to the raw data. As a concrete problem, we study a multivariate…

Statistics Theory · Mathematics 2021-10-22 Thomas Berrett , Yi Yu

We address the problem of non-parametric density estimation under the additional constraint that only privatised data are allowed to be published and available for inference. For this purpose, we adopt a recent generalisation of classical…

Statistics Theory · Mathematics 2019-03-06 Cristina Butucea , Amandine Dubois , Martin Kroll , Adrien Saumard

We study statistical estimation under local differential privacy (LDP) when users may hold heterogeneous privacy levels and accuracy must be guaranteed with high probability. Departing from the common in-expectation analyses, and for…

Machine Learning · Statistics 2025-10-15 Maryam Aliakbarpour , Alireza Fallah , Swaha Roy , Ria Stevens

In differential privacy, random noise is introduced to privatize summary statistics of a sensitive dataset before releasing them. The noise level determines the privacy loss, which quantifies how easily an adversary can detect a target…

Statistics Theory · Mathematics 2026-02-24 Youngjoo Yun , Rishabh Dudeja