A privacy-preserving framework for ranked retrieval model

Tong Yan, Yunpeng Gao, Nan Zhang

Research output: Contribution to journalArticle

Abstract

In this paper, we address privacy issues related to ranked retrieval model in web databases, each of which takes private attributes as part of input in the ranking function. Many web databases keep private attributes invisible to public and believe that the adversary is unable to reveal the private attribute values from query results. However, prior research (Rahman et al. in Proc VLDB Endow 8:1106–17, 2015) studied the problem of rank-based inference of private attributes over web databases. They found that one can infer the value of private attributes of a victim tuple by issuing well-designed queries through a top-k query interface. To address the privacy issue, in this paper, we propose a novel privacy-preserving framework. Our framework protects private attributes’ privacy not only under inference attacks but also under arbitrary attack methods. In particular, we classify adversaries into two widely existing categories: domain-ignorant and domain-expert adversaries. Then, we develop equivalent set with virtual tuples (ESVT) for domain-ignorant adversaries and equivalent set with true tuples (ESTT) for domain-expert adversaries. The ESVT and the ESTT are the primary parts of our privacy-preserving framework. To evaluate the performance, we define a measurement of privacy guarantee for private attributes and measurements for utility loss. We prove that both ESVT and ESTT achieve the privacy guarantee. We also develop heuristic algorithms for ESVT and ESTT, respectively, under the consideration of minimizing utility loss. We demonstrate the effectiveness of our techniques through theoretical analysis and extensive experiments over real-world dataset.

Original languageEnglish (US)
Article number6
JournalComputational Social Networks
Volume6
Issue number1
DOIs
StatePublished - Dec 1 2019

Fingerprint

Equivalent sets
Privacy Preserving
Retrieval
Attribute
Privacy
Heuristic algorithms
Query
Model
Attack
Ranking Function
Framework
Experiments
Heuristic algorithm
Theoretical Analysis
Classify

All Science Journal Classification (ASJC) codes

  • Information Systems
  • Modeling and Simulation
  • Human-Computer Interaction
  • Computer Science Applications

Cite this

Yan, Tong ; Gao, Yunpeng ; Zhang, Nan. / A privacy-preserving framework for ranked retrieval model. In: Computational Social Networks. 2019 ; Vol. 6, No. 1.
@article{f78e7161b2e14bc8aa097619b751c6ae,
title = "A privacy-preserving framework for ranked retrieval model",
abstract = "In this paper, we address privacy issues related to ranked retrieval model in web databases, each of which takes private attributes as part of input in the ranking function. Many web databases keep private attributes invisible to public and believe that the adversary is unable to reveal the private attribute values from query results. However, prior research (Rahman et al. in Proc VLDB Endow 8:1106–17, 2015) studied the problem of rank-based inference of private attributes over web databases. They found that one can infer the value of private attributes of a victim tuple by issuing well-designed queries through a top-k query interface. To address the privacy issue, in this paper, we propose a novel privacy-preserving framework. Our framework protects private attributes’ privacy not only under inference attacks but also under arbitrary attack methods. In particular, we classify adversaries into two widely existing categories: domain-ignorant and domain-expert adversaries. Then, we develop equivalent set with virtual tuples (ESVT) for domain-ignorant adversaries and equivalent set with true tuples (ESTT) for domain-expert adversaries. The ESVT and the ESTT are the primary parts of our privacy-preserving framework. To evaluate the performance, we define a measurement of privacy guarantee for private attributes and measurements for utility loss. We prove that both ESVT and ESTT achieve the privacy guarantee. We also develop heuristic algorithms for ESVT and ESTT, respectively, under the consideration of minimizing utility loss. We demonstrate the effectiveness of our techniques through theoretical analysis and extensive experiments over real-world dataset.",
author = "Tong Yan and Yunpeng Gao and Nan Zhang",
year = "2019",
month = "12",
day = "1",
doi = "10.1186/s40649-019-0067-0",
language = "English (US)",
volume = "6",
journal = "Computational Social Networks",
issn = "2197-4314",
publisher = "SpringerOpen",
number = "1",

}

A privacy-preserving framework for ranked retrieval model. / Yan, Tong; Gao, Yunpeng; Zhang, Nan.

In: Computational Social Networks, Vol. 6, No. 1, 6, 01.12.2019.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A privacy-preserving framework for ranked retrieval model

AU - Yan, Tong

AU - Gao, Yunpeng

AU - Zhang, Nan

PY - 2019/12/1

Y1 - 2019/12/1

N2 - In this paper, we address privacy issues related to ranked retrieval model in web databases, each of which takes private attributes as part of input in the ranking function. Many web databases keep private attributes invisible to public and believe that the adversary is unable to reveal the private attribute values from query results. However, prior research (Rahman et al. in Proc VLDB Endow 8:1106–17, 2015) studied the problem of rank-based inference of private attributes over web databases. They found that one can infer the value of private attributes of a victim tuple by issuing well-designed queries through a top-k query interface. To address the privacy issue, in this paper, we propose a novel privacy-preserving framework. Our framework protects private attributes’ privacy not only under inference attacks but also under arbitrary attack methods. In particular, we classify adversaries into two widely existing categories: domain-ignorant and domain-expert adversaries. Then, we develop equivalent set with virtual tuples (ESVT) for domain-ignorant adversaries and equivalent set with true tuples (ESTT) for domain-expert adversaries. The ESVT and the ESTT are the primary parts of our privacy-preserving framework. To evaluate the performance, we define a measurement of privacy guarantee for private attributes and measurements for utility loss. We prove that both ESVT and ESTT achieve the privacy guarantee. We also develop heuristic algorithms for ESVT and ESTT, respectively, under the consideration of minimizing utility loss. We demonstrate the effectiveness of our techniques through theoretical analysis and extensive experiments over real-world dataset.

AB - In this paper, we address privacy issues related to ranked retrieval model in web databases, each of which takes private attributes as part of input in the ranking function. Many web databases keep private attributes invisible to public and believe that the adversary is unable to reveal the private attribute values from query results. However, prior research (Rahman et al. in Proc VLDB Endow 8:1106–17, 2015) studied the problem of rank-based inference of private attributes over web databases. They found that one can infer the value of private attributes of a victim tuple by issuing well-designed queries through a top-k query interface. To address the privacy issue, in this paper, we propose a novel privacy-preserving framework. Our framework protects private attributes’ privacy not only under inference attacks but also under arbitrary attack methods. In particular, we classify adversaries into two widely existing categories: domain-ignorant and domain-expert adversaries. Then, we develop equivalent set with virtual tuples (ESVT) for domain-ignorant adversaries and equivalent set with true tuples (ESTT) for domain-expert adversaries. The ESVT and the ESTT are the primary parts of our privacy-preserving framework. To evaluate the performance, we define a measurement of privacy guarantee for private attributes and measurements for utility loss. We prove that both ESVT and ESTT achieve the privacy guarantee. We also develop heuristic algorithms for ESVT and ESTT, respectively, under the consideration of minimizing utility loss. We demonstrate the effectiveness of our techniques through theoretical analysis and extensive experiments over real-world dataset.

UR - http://www.scopus.com/inward/record.url?scp=85069469945&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85069469945&partnerID=8YFLogxK

U2 - 10.1186/s40649-019-0067-0

DO - 10.1186/s40649-019-0067-0

M3 - Article

VL - 6

JO - Computational Social Networks

JF - Computational Social Networks

SN - 2197-4314

IS - 1

M1 - 6

ER -