A Generalization of the Stratonovich's Value of Information and Application to Privacy-Utility Trade-off

Akira Kamatsuka; Takahiro Yoshida; Toshiyasu Matsushima

doi:10.1109/ISIT50566.2022.9834667

A Generalization of the Stratonovich's Value of Information and Application to Privacy-Utility Trade-off

Akira Kamatsuka, Takahiro Yoshida, Toshiyasu Matsushima

School of Fundamental Science and Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Citation (Scopus)

Abstract

The Stratonovich's value of information (VoI) is quantity that measures how much inferential gain is obtained from noisy data under information leakage constraint. In this paper, we introduce a generalized VoI for a general loss function and general information leakage. Then we derive an upper bound of the generalized VoI. Moreover, for a classical loss function, we provide a achievable condition of the upper bound which is weaker than that of in previous studies. Since VoI can be viewed as a formulation of a privacy-utility trade-off (PUT) problem, we provide an interpretation of the achievable condition in the PUT context.

Original language	English
Title of host publication	2022 IEEE International Symposium on Information Theory, ISIT 2022
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1999-2004
Number of pages	6
ISBN (Electronic)	9781665421591
DOIs	https://doi.org/10.1109/ISIT50566.2022.9834667
Publication status	Published - 2022
Event	2022 IEEE International Symposium on Information Theory, ISIT 2022 - Espoo, Finland Duration: 2022 Jun 26 → 2022 Jul 1

Publication series

Name	IEEE International Symposium on Information Theory - Proceedings
Volume	2022-June
ISSN (Print)	2157-8095

Conference

Conference	2022 IEEE International Symposium on Information Theory, ISIT 2022
Country/Territory	Finland
City	Espoo
Period	22/6/26 → 22/7/1

ASJC Scopus subject areas

Theoretical Computer Science
Information Systems
Modelling and Simulation
Applied Mathematics

Access to Document

10.1109/ISIT50566.2022.9834667

Cite this

Kamatsuka, A., Yoshida, T., & Matsushima, T. (2022). A Generalization of the Stratonovich's Value of Information and Application to Privacy-Utility Trade-off. In 2022 IEEE International Symposium on Information Theory, ISIT 2022 (pp. 1999-2004). (IEEE International Symposium on Information Theory - Proceedings; Vol. 2022-June). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ISIT50566.2022.9834667

A Generalization of the Stratonovich's Value of Information and Application to Privacy-Utility Trade-off. / Kamatsuka, Akira; Yoshida, Takahiro; Matsushima, Toshiyasu.
2022 IEEE International Symposium on Information Theory, ISIT 2022. Institute of Electrical and Electronics Engineers Inc., 2022. p. 1999-2004 (IEEE International Symposium on Information Theory - Proceedings; Vol. 2022-June).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Kamatsuka, A, Yoshida, T & Matsushima, T 2022, A Generalization of the Stratonovich's Value of Information and Application to Privacy-Utility Trade-off. in 2022 IEEE International Symposium on Information Theory, ISIT 2022. IEEE International Symposium on Information Theory - Proceedings, vol. 2022-June, Institute of Electrical and Electronics Engineers Inc., pp. 1999-2004, 2022 IEEE International Symposium on Information Theory, ISIT 2022, Espoo, Finland, 22/6/26. https://doi.org/10.1109/ISIT50566.2022.9834667

Kamatsuka A, Yoshida T, Matsushima T. A Generalization of the Stratonovich's Value of Information and Application to Privacy-Utility Trade-off. In 2022 IEEE International Symposium on Information Theory, ISIT 2022. Institute of Electrical and Electronics Engineers Inc. 2022. p. 1999-2004. (IEEE International Symposium on Information Theory - Proceedings). doi: 10.1109/ISIT50566.2022.9834667

Kamatsuka, Akira ; Yoshida, Takahiro ; Matsushima, Toshiyasu. / A Generalization of the Stratonovich's Value of Information and Application to Privacy-Utility Trade-off. 2022 IEEE International Symposium on Information Theory, ISIT 2022. Institute of Electrical and Electronics Engineers Inc., 2022. pp. 1999-2004 (IEEE International Symposium on Information Theory - Proceedings).

@inproceedings{54545d234e2d4578bc12776c9a38189f,

title = "A Generalization of the Stratonovich's Value of Information and Application to Privacy-Utility Trade-off",

abstract = "The Stratonovich's value of information (VoI) is quantity that measures how much inferential gain is obtained from noisy data under information leakage constraint. In this paper, we introduce a generalized VoI for a general loss function and general information leakage. Then we derive an upper bound of the generalized VoI. Moreover, for a classical loss function, we provide a achievable condition of the upper bound which is weaker than that of in previous studies. Since VoI can be viewed as a formulation of a privacy-utility trade-off (PUT) problem, we provide an interpretation of the achievable condition in the PUT context.",

author = "Akira Kamatsuka and Takahiro Yoshida and Toshiyasu Matsushima",

note = "Funding Information: This research is supported in part by Grant-in-Aid JP17K06446 for Scientific Research (C). Publisher Copyright: {\textcopyright} 2022 IEEE.; 2022 IEEE International Symposium on Information Theory, ISIT 2022 ; Conference date: 26-06-2022 Through 01-07-2022",

year = "2022",

doi = "10.1109/ISIT50566.2022.9834667",

language = "English",

series = "IEEE International Symposium on Information Theory - Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "1999--2004",

booktitle = "2022 IEEE International Symposium on Information Theory, ISIT 2022",

}

TY - GEN

T1 - A Generalization of the Stratonovich's Value of Information and Application to Privacy-Utility Trade-off

AU - Kamatsuka, Akira

AU - Yoshida, Takahiro

AU - Matsushima, Toshiyasu

PY - 2022

Y1 - 2022

N2 - The Stratonovich's value of information (VoI) is quantity that measures how much inferential gain is obtained from noisy data under information leakage constraint. In this paper, we introduce a generalized VoI for a general loss function and general information leakage. Then we derive an upper bound of the generalized VoI. Moreover, for a classical loss function, we provide a achievable condition of the upper bound which is weaker than that of in previous studies. Since VoI can be viewed as a formulation of a privacy-utility trade-off (PUT) problem, we provide an interpretation of the achievable condition in the PUT context.

AB - The Stratonovich's value of information (VoI) is quantity that measures how much inferential gain is obtained from noisy data under information leakage constraint. In this paper, we introduce a generalized VoI for a general loss function and general information leakage. Then we derive an upper bound of the generalized VoI. Moreover, for a classical loss function, we provide a achievable condition of the upper bound which is weaker than that of in previous studies. Since VoI can be viewed as a formulation of a privacy-utility trade-off (PUT) problem, we provide an interpretation of the achievable condition in the PUT context.

UR - http://www.scopus.com/inward/record.url?scp=85136260033&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85136260033&partnerID=8YFLogxK

U2 - 10.1109/ISIT50566.2022.9834667

DO - 10.1109/ISIT50566.2022.9834667

M3 - Conference contribution

AN - SCOPUS:85136260033

T3 - IEEE International Symposium on Information Theory - Proceedings

SP - 1999

EP - 2004

BT - 2022 IEEE International Symposium on Information Theory, ISIT 2022

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2022 IEEE International Symposium on Information Theory, ISIT 2022

Y2 - 26 June 2022 through 1 July 2022

ER -

A Generalization of the Stratonovich's Value of Information and Application to Privacy-Utility Trade-off

Abstract

Publication series

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this