Aggregate query answering on anonymized tables

Qing Zhang, Nick Koudas, Divesh Srivastava, Ting Yu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

215 Citations (Scopus)

Abstract

Privacy is a serious concern when microdata need to be released for ad hoc analyses. The privacy goals of existing privacy protection approaches (e.g., k-anonymity and ℓ-diversity) are suitable only for categorical sensitive attributes. Since applying them directly to numerical sensitive attributes (e.g., salary) may result in undesirable information leakage, we propose privacy goals to better capture the need of privacy protection for numerical sensitive attributes. Complementing the desire for privacy is the need to support ad hoc aggregate analyses over microdata. Existing generalization-based anonymization approaches cannot answer aggregate queries with reasonable accuracy. We present a general framework of permutation-based anonymization to support accurate answering of aggregate queries and show that, for the same grouping, permutation-based techniques can always answer aggregate queries more accurately than generalization-based approaches. We further propose several criteria to optimize permutations for accurate answering of aggregate queries, and develop efficient algorithms for each criterion.

Original languageEnglish
Title of host publicationProceedings - International Conference on Data Engineering
Pages116-125
Number of pages10
DOIs
Publication statusPublished - 24 Sep 2007
Externally publishedYes
Event23rd International Conference on Data Engineering, ICDE 2007 - Istanbul, Turkey
Duration: 15 Apr 200720 Apr 2007

Other

Other23rd International Conference on Data Engineering, ICDE 2007
CountryTurkey
CityIstanbul
Period15/4/0720/4/07

Fingerprint

Wages

ASJC Scopus subject areas

  • Software
  • Engineering(all)
  • Engineering (miscellaneous)

Cite this

Zhang, Q., Koudas, N., Srivastava, D., & Yu, T. (2007). Aggregate query answering on anonymized tables. In Proceedings - International Conference on Data Engineering (pp. 116-125). [4221660] https://doi.org/10.1109/ICDE.2007.367857

Aggregate query answering on anonymized tables. / Zhang, Qing; Koudas, Nick; Srivastava, Divesh; Yu, Ting.

Proceedings - International Conference on Data Engineering. 2007. p. 116-125 4221660.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Zhang, Q, Koudas, N, Srivastava, D & Yu, T 2007, Aggregate query answering on anonymized tables. in Proceedings - International Conference on Data Engineering., 4221660, pp. 116-125, 23rd International Conference on Data Engineering, ICDE 2007, Istanbul, Turkey, 15/4/07. https://doi.org/10.1109/ICDE.2007.367857
Zhang Q, Koudas N, Srivastava D, Yu T. Aggregate query answering on anonymized tables. In Proceedings - International Conference on Data Engineering. 2007. p. 116-125. 4221660 https://doi.org/10.1109/ICDE.2007.367857
Zhang, Qing ; Koudas, Nick ; Srivastava, Divesh ; Yu, Ting. / Aggregate query answering on anonymized tables. Proceedings - International Conference on Data Engineering. 2007. pp. 116-125
@inproceedings{fa6444f705e542148840c9b16c320fbe,
title = "Aggregate query answering on anonymized tables",
abstract = "Privacy is a serious concern when microdata need to be released for ad hoc analyses. The privacy goals of existing privacy protection approaches (e.g., k-anonymity and ℓ-diversity) are suitable only for categorical sensitive attributes. Since applying them directly to numerical sensitive attributes (e.g., salary) may result in undesirable information leakage, we propose privacy goals to better capture the need of privacy protection for numerical sensitive attributes. Complementing the desire for privacy is the need to support ad hoc aggregate analyses over microdata. Existing generalization-based anonymization approaches cannot answer aggregate queries with reasonable accuracy. We present a general framework of permutation-based anonymization to support accurate answering of aggregate queries and show that, for the same grouping, permutation-based techniques can always answer aggregate queries more accurately than generalization-based approaches. We further propose several criteria to optimize permutations for accurate answering of aggregate queries, and develop efficient algorithms for each criterion.",
author = "Qing Zhang and Nick Koudas and Divesh Srivastava and Ting Yu",
year = "2007",
month = "9",
day = "24",
doi = "10.1109/ICDE.2007.367857",
language = "English",
isbn = "1424408032",
pages = "116--125",
booktitle = "Proceedings - International Conference on Data Engineering",

}

TY - GEN

T1 - Aggregate query answering on anonymized tables

AU - Zhang, Qing

AU - Koudas, Nick

AU - Srivastava, Divesh

AU - Yu, Ting

PY - 2007/9/24

Y1 - 2007/9/24

N2 - Privacy is a serious concern when microdata need to be released for ad hoc analyses. The privacy goals of existing privacy protection approaches (e.g., k-anonymity and ℓ-diversity) are suitable only for categorical sensitive attributes. Since applying them directly to numerical sensitive attributes (e.g., salary) may result in undesirable information leakage, we propose privacy goals to better capture the need of privacy protection for numerical sensitive attributes. Complementing the desire for privacy is the need to support ad hoc aggregate analyses over microdata. Existing generalization-based anonymization approaches cannot answer aggregate queries with reasonable accuracy. We present a general framework of permutation-based anonymization to support accurate answering of aggregate queries and show that, for the same grouping, permutation-based techniques can always answer aggregate queries more accurately than generalization-based approaches. We further propose several criteria to optimize permutations for accurate answering of aggregate queries, and develop efficient algorithms for each criterion.

AB - Privacy is a serious concern when microdata need to be released for ad hoc analyses. The privacy goals of existing privacy protection approaches (e.g., k-anonymity and ℓ-diversity) are suitable only for categorical sensitive attributes. Since applying them directly to numerical sensitive attributes (e.g., salary) may result in undesirable information leakage, we propose privacy goals to better capture the need of privacy protection for numerical sensitive attributes. Complementing the desire for privacy is the need to support ad hoc aggregate analyses over microdata. Existing generalization-based anonymization approaches cannot answer aggregate queries with reasonable accuracy. We present a general framework of permutation-based anonymization to support accurate answering of aggregate queries and show that, for the same grouping, permutation-based techniques can always answer aggregate queries more accurately than generalization-based approaches. We further propose several criteria to optimize permutations for accurate answering of aggregate queries, and develop efficient algorithms for each criterion.

UR - http://www.scopus.com/inward/record.url?scp=34548710709&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34548710709&partnerID=8YFLogxK

U2 - 10.1109/ICDE.2007.367857

DO - 10.1109/ICDE.2007.367857

M3 - Conference contribution

SN - 1424408032

SN - 9781424408030

SP - 116

EP - 125

BT - Proceedings - International Conference on Data Engineering

ER -