Functional mechanism: Regression analysis under differential privacy

Jun Zhang, Zhenjie Zhang, Xiaokui Xiao, Yin Yang, Marianne Winslett

Research output: Contribution to journalArticle

109 Citations (Scopus)

Abstract

∈-differential privacy is the state-of-the-art model for releasing sensitive information while protecting privacy. Numerous methods have been proposed to enforce ?-differential privacy in various analytical tasks, e.g., regression analysis. Existing solutions for regression analysis, however, are either limited to non-standard types of regression or unable to produce accurate regression results. Motivated by this, we propose the Functional Mechanism, a differentially private method designed for a large class of optimizationbased analyses. The main idea is to enforce ∈-differential privacy by perturbing the objective function of the optimization problem, rather than its results. As case studies, we apply the functional mechanism to address two most widely used regression models, namely, linear regression and logistic regression. Both theoretical analysis and thorough experimental evaluations show that the functional mechanism is highly effective and efficient, and it significantly outperforms existing solutions.

Original languageEnglish
Pages (from-to)1364-1375
Number of pages12
JournalProceedings of the VLDB Endowment
Volume5
Issue number11
Publication statusPublished - Jul 2012
Externally publishedYes

Fingerprint

Regression analysis
Linear regression
Logistics

ASJC Scopus subject areas

  • Computer Science (miscellaneous)
  • Computer Science(all)

Cite this

Zhang, J., Zhang, Z., Xiao, X., Yang, Y., & Winslett, M. (2012). Functional mechanism: Regression analysis under differential privacy. Proceedings of the VLDB Endowment, 5(11), 1364-1375.

Functional mechanism : Regression analysis under differential privacy. / Zhang, Jun; Zhang, Zhenjie; Xiao, Xiaokui; Yang, Yin; Winslett, Marianne.

In: Proceedings of the VLDB Endowment, Vol. 5, No. 11, 07.2012, p. 1364-1375.

Research output: Contribution to journalArticle

Zhang, J, Zhang, Z, Xiao, X, Yang, Y & Winslett, M 2012, 'Functional mechanism: Regression analysis under differential privacy', Proceedings of the VLDB Endowment, vol. 5, no. 11, pp. 1364-1375.
Zhang, Jun ; Zhang, Zhenjie ; Xiao, Xiaokui ; Yang, Yin ; Winslett, Marianne. / Functional mechanism : Regression analysis under differential privacy. In: Proceedings of the VLDB Endowment. 2012 ; Vol. 5, No. 11. pp. 1364-1375.
@article{b3d2515133ee4f43a78cef652f07daa3,
title = "Functional mechanism: Regression analysis under differential privacy",
abstract = "∈-differential privacy is the state-of-the-art model for releasing sensitive information while protecting privacy. Numerous methods have been proposed to enforce ?-differential privacy in various analytical tasks, e.g., regression analysis. Existing solutions for regression analysis, however, are either limited to non-standard types of regression or unable to produce accurate regression results. Motivated by this, we propose the Functional Mechanism, a differentially private method designed for a large class of optimizationbased analyses. The main idea is to enforce ∈-differential privacy by perturbing the objective function of the optimization problem, rather than its results. As case studies, we apply the functional mechanism to address two most widely used regression models, namely, linear regression and logistic regression. Both theoretical analysis and thorough experimental evaluations show that the functional mechanism is highly effective and efficient, and it significantly outperforms existing solutions.",
author = "Jun Zhang and Zhenjie Zhang and Xiaokui Xiao and Yin Yang and Marianne Winslett",
year = "2012",
month = "7",
language = "English",
volume = "5",
pages = "1364--1375",
journal = "Proceedings of the VLDB Endowment",
issn = "2150-8097",
publisher = "Very Large Data Base Endowment Inc.",
number = "11",

}

TY - JOUR

T1 - Functional mechanism

T2 - Regression analysis under differential privacy

AU - Zhang, Jun

AU - Zhang, Zhenjie

AU - Xiao, Xiaokui

AU - Yang, Yin

AU - Winslett, Marianne

PY - 2012/7

Y1 - 2012/7

N2 - ∈-differential privacy is the state-of-the-art model for releasing sensitive information while protecting privacy. Numerous methods have been proposed to enforce ?-differential privacy in various analytical tasks, e.g., regression analysis. Existing solutions for regression analysis, however, are either limited to non-standard types of regression or unable to produce accurate regression results. Motivated by this, we propose the Functional Mechanism, a differentially private method designed for a large class of optimizationbased analyses. The main idea is to enforce ∈-differential privacy by perturbing the objective function of the optimization problem, rather than its results. As case studies, we apply the functional mechanism to address two most widely used regression models, namely, linear regression and logistic regression. Both theoretical analysis and thorough experimental evaluations show that the functional mechanism is highly effective and efficient, and it significantly outperforms existing solutions.

AB - ∈-differential privacy is the state-of-the-art model for releasing sensitive information while protecting privacy. Numerous methods have been proposed to enforce ?-differential privacy in various analytical tasks, e.g., regression analysis. Existing solutions for regression analysis, however, are either limited to non-standard types of regression or unable to produce accurate regression results. Motivated by this, we propose the Functional Mechanism, a differentially private method designed for a large class of optimizationbased analyses. The main idea is to enforce ∈-differential privacy by perturbing the objective function of the optimization problem, rather than its results. As case studies, we apply the functional mechanism to address two most widely used regression models, namely, linear regression and logistic regression. Both theoretical analysis and thorough experimental evaluations show that the functional mechanism is highly effective and efficient, and it significantly outperforms existing solutions.

UR - http://www.scopus.com/inward/record.url?scp=84873178476&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84873178476&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:84873178476

VL - 5

SP - 1364

EP - 1375

JO - Proceedings of the VLDB Endowment

JF - Proceedings of the VLDB Endowment

SN - 2150-8097

IS - 11

ER -