Boosting the accuracy of differentially private histograms through consistency
Michael Hay,Vibhor Rastogi,Gerome Miklau,Dan Suciu +3 more
- 01 Sep 2010
- Vol. 3, Iss: 1, pp 1021-1032
TL;DR: It is shown that it is possible to significantly improve the accuracy of a general class of histogram queries while satisfying differential privacy, and that these techniques can be used for estimating the degree sequence of a graph very precisely, and for computing a histogram that can support arbitrary range queries accurately.
read more
Abstract: We show that it is possible to significantly improve the accuracy of a general class of histogram queries while satisfying differential privacy. Our approach carefully chooses a set of queries to evaluate, and then exploits consistency constraints that should hold over the noisy output. In a post-processing phase, we compute the consistent input most likely to have produced the noisy output. The final output is differentially-private and consistent, but in addition, it is often much more accurate. We show, both theoretically and experimentally, that these techniques can be used for estimating the degree sequence of a graph very precisely, and for computing a histogram that can support arbitrary range queries accurately.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Differentially private grids for geospatial data
Wahbeh Qardaji,Weining Yang,Ninghui Li +2 more
- 08 Apr 2013
TL;DR: This paper proposes a method for choosing a grid size for two-dimensional datasets such as geospatial datasets, and introduces a novel adaptive-grid method, which exploits the need to have finer granularity partitioning over dense regions and, at the same time, coarse partitions over sparse regions.
Analyzing Your Location Data with Provable Privacy Guarantees
Ashwin Machanavajjhala,Xi He +1 more
- 01 Jan 2018
TL;DR: This chapter highlights the privacy concerns in large-scale collections of location data from user-centric mobile devices and explains how simple cloaking based techniques might be ineffective, and motivates the need for algorithms that collect and analyze location data with formal provable privacy guarantees.
The scaling limit of critical Ising interfaces is $\mathrm{CLE}_{3}$
Stéphane Benoist,Clément Hongler +1 more
TL;DR: In this paper, the authors consider the set of interfaces between $+$ and $-$ spins arising for the critical planar Ising model on a domain with boundary conditions, and show that it converges to nested CLE$3}.
A Deep Learning-based Data Usability Enhancement Scheme for Differential Privacy
Haonan Yan,Xiaoguang Li,Gewei Zheng,Hui Li,Fenghua Li,Xiao-La Lin +5 more
- 28 Aug 2023
TL;DR: A novel deep learning-based data usability enhancement scheme for differential privacy that is data-type independent and reduces the mean square error (MSE) of DP-perturbed data.
Synthesizing Privacy-Preserving Traces: Enhancing Plausibility with Social Networks
Guanglin Zhang,Ping Zhao,Anqi Zhang +2 more
TL;DR: Synthesizing privacy-preserving traces with enhanced plausibility on social networks. The existing work suffers from social relationship based de-anonymization attacks. $$W^3\text{-}tess$$ synthesizes traces that exhibit similar three-dimension mobility behavior and provides differential privacy.
References
The Structure and Function of Complex Networks
TL;DR: Developments in this field are reviewed, including such concepts as the small-world effect, degree distributions, clustering, network correlations, random graph models, models of network growth and preferential attachment, and dynamical processes taking place on networks.
Calibrating noise to sensitivity in private data analysis
Cynthia Dwork,Frank McSherry,Kobbi Nissim,Adam Smith +3 more
- 04 Mar 2006
TL;DR: In this article, the authors show that for several particular applications substantially less noise is needed than was previously understood to be the case, and also show the separation results showing the increased value of interactive sanitization mechanisms over non-interactive.
Differential privacy: a survey of results
Cynthia Dwork
- 25 Apr 2008
TL;DR: This survey recalls the definition of differential privacy and two basic techniques for achieving it, and shows some interesting applications of these techniques, presenting algorithms for three specific tasks and three general results on differentially private learning.
•Journal Article
Calibrating noise to sensitivity in private data analysis
TL;DR: The study is extended to general functions f, proving that privacy can be preserved by calibrating the standard deviation of the noise according to the sensitivity of the function f, which is the amount that any single argument to f can change its output.
3.6K
The Trouble with Wilderness; Or, Getting Back to the Wrong Nature
TL;DR: Wilderness hides its unnaturalness behind a mask that is all the more beguiling because it seems so natural as mentioned in this paper, and we too easily imagine that what we gaze into the mirror it holds up for us, when in fact we see the reflection of our own unexamined longings and desires.
Related Papers (5)
[...]
Cynthia Dwork
- 10 Jul 2006
Kobbi Nissim,Sofya Raskhodnikova,Adam Smith +2 more
- 11 Jun 2007
Cynthia Dwork
- 25 Apr 2008