Privacy-Preserving Correlation Coefficient
Summary :
Differential privacy is a confidentiality metric and quantitatively guarantees the confidentiality of individuals. A noise criterion, called sensitivity, must be calculated when constructing a probabilistic disturbance mechanism that satisfies differential privacy. Depending on the statistical process, the sensitivity may be very large or even impossible to compute. As a result, the usefulness of the constructed mechanism may be significantly low; it might even be impossible to directly construct it. In this paper, we first discuss situations in which sensitivity is difficult to calculate, and then propose a differential privacy with additional dummy data as a countermeasure. When the sensitivity in the conventional differential privacy is calculable, a mechanism that satisfies the proposed metric satisfies the conventional differential privacy at the same time, and it is possible to evaluate the relationship between the respective privacy parameters. Next, we derive sensitivity by focusing on correlation coefficients as a case study of a statistical process for which sensitivity is difficult to calculate, and propose a probabilistic disturbing mechanism that satisfies the proposed metric. Finally, we experimentally evaluate the effect of noise on the sensitivity of the proposed and direct methods. Experiments show that privacy-preserving correlation coefficients can be derived with less noise compared to using direct methods.
- Publication
- IEICE TRANSACTIONS on Information Vol.E106-D No.5 pp.868-876
- Publication Date
- 2023/05/01
- Publicized
- 2023/02/08
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.2022DAP0014
- Type of Manuscript
- Special Section PAPER (Special Section on Data Engineering and Information Management)
- Category
Authors
Tomoaki MIMOTO
Advanced Telecommunications Research Institute International (ATR)
Hiroyuki YOKOYAMA
Advanced Telecommunications Research Institute International (ATR)
Toru NAKAMURA
KDDI Research, Inc.
Takamasa ISOHARA
KDDI Research, Inc.
Masayuki HASHIMOTO
KDDI Research, Inc.
Ryosuke KOJIMA
Kyoto University
Aki HASEGAWA
Kyoto University
Yasushi OKUNO
Kyoto University
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Tomoaki MIMOTO, Hiroyuki YOKOYAMA, Toru NAKAMURA, Takamasa ISOHARA, Masayuki HASHIMOTO, Ryosuke KOJIMA, Aki HASEGAWA, Yasushi OKUNO, "Privacy-Preserving Correlation Coefficient" in IEICE TRANSACTIONS on Information,
vol. E106-D, no. 5, pp. 868-876, May 2023, doi: 10.1587/transinf.2022DAP0014.
Abstract: Differential privacy is a confidentiality metric and quantitatively guarantees the confidentiality of individuals. A noise criterion, called sensitivity, must be calculated when constructing a probabilistic disturbance mechanism that satisfies differential privacy. Depending on the statistical process, the sensitivity may be very large or even impossible to compute. As a result, the usefulness of the constructed mechanism may be significantly low; it might even be impossible to directly construct it. In this paper, we first discuss situations in which sensitivity is difficult to calculate, and then propose a differential privacy with additional dummy data as a countermeasure. When the sensitivity in the conventional differential privacy is calculable, a mechanism that satisfies the proposed metric satisfies the conventional differential privacy at the same time, and it is possible to evaluate the relationship between the respective privacy parameters. Next, we derive sensitivity by focusing on correlation coefficients as a case study of a statistical process for which sensitivity is difficult to calculate, and propose a probabilistic disturbing mechanism that satisfies the proposed metric. Finally, we experimentally evaluate the effect of noise on the sensitivity of the proposed and direct methods. Experiments show that privacy-preserving correlation coefficients can be derived with less noise compared to using direct methods.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2022DAP0014/_p
Copy
@ARTICLE{e106-d_5_868,
author={Tomoaki MIMOTO, Hiroyuki YOKOYAMA, Toru NAKAMURA, Takamasa ISOHARA, Masayuki HASHIMOTO, Ryosuke KOJIMA, Aki HASEGAWA, Yasushi OKUNO, },
journal={IEICE TRANSACTIONS on Information},
title={Privacy-Preserving Correlation Coefficient},
year={2023},
volume={E106-D},
number={5},
pages={868-876},
abstract={Differential privacy is a confidentiality metric and quantitatively guarantees the confidentiality of individuals. A noise criterion, called sensitivity, must be calculated when constructing a probabilistic disturbance mechanism that satisfies differential privacy. Depending on the statistical process, the sensitivity may be very large or even impossible to compute. As a result, the usefulness of the constructed mechanism may be significantly low; it might even be impossible to directly construct it. In this paper, we first discuss situations in which sensitivity is difficult to calculate, and then propose a differential privacy with additional dummy data as a countermeasure. When the sensitivity in the conventional differential privacy is calculable, a mechanism that satisfies the proposed metric satisfies the conventional differential privacy at the same time, and it is possible to evaluate the relationship between the respective privacy parameters. Next, we derive sensitivity by focusing on correlation coefficients as a case study of a statistical process for which sensitivity is difficult to calculate, and propose a probabilistic disturbing mechanism that satisfies the proposed metric. Finally, we experimentally evaluate the effect of noise on the sensitivity of the proposed and direct methods. Experiments show that privacy-preserving correlation coefficients can be derived with less noise compared to using direct methods.},
keywords={},
doi={10.1587/transinf.2022DAP0014},
ISSN={1745-1361},
month={May},}
Copy
TY - JOUR
TI - Privacy-Preserving Correlation Coefficient
T2 - IEICE TRANSACTIONS on Information
SP - 868
EP - 876
AU - Tomoaki MIMOTO
AU - Hiroyuki YOKOYAMA
AU - Toru NAKAMURA
AU - Takamasa ISOHARA
AU - Masayuki HASHIMOTO
AU - Ryosuke KOJIMA
AU - Aki HASEGAWA
AU - Yasushi OKUNO
PY - 2023
DO - 10.1587/transinf.2022DAP0014
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E106-D
IS - 5
JA - IEICE TRANSACTIONS on Information
Y1 - May 2023
AB - Differential privacy is a confidentiality metric and quantitatively guarantees the confidentiality of individuals. A noise criterion, called sensitivity, must be calculated when constructing a probabilistic disturbance mechanism that satisfies differential privacy. Depending on the statistical process, the sensitivity may be very large or even impossible to compute. As a result, the usefulness of the constructed mechanism may be significantly low; it might even be impossible to directly construct it. In this paper, we first discuss situations in which sensitivity is difficult to calculate, and then propose a differential privacy with additional dummy data as a countermeasure. When the sensitivity in the conventional differential privacy is calculable, a mechanism that satisfies the proposed metric satisfies the conventional differential privacy at the same time, and it is possible to evaluate the relationship between the respective privacy parameters. Next, we derive sensitivity by focusing on correlation coefficients as a case study of a statistical process for which sensitivity is difficult to calculate, and propose a probabilistic disturbing mechanism that satisfies the proposed metric. Finally, we experimentally evaluate the effect of noise on the sensitivity of the proposed and direct methods. Experiments show that privacy-preserving correlation coefficients can be derived with less noise compared to using direct methods.
ER -
English
