Privacy-Utility Management of Hypothesis Tests

被引:0
|
作者
Li, Zuxing [1 ,2 ]
Oechtering, Tobias J. [3 ]
机构
[1] Cent Supelec, Paris, France
[2] L2S, Paris, France
[3] KTH Royal Inst Technol, EECS, Stockholm, Sweden
基金
瑞典研究理事会;
关键词
ENERGY;
D O I
暂无
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
The trade-off of hypothesis tests on the correlated privacy hypothesis and utility hypothesis is studied. The error exponent of the Bayesian composite hypothesis test on the privacy or utility hypothesis can be characterized by the corresponding minimal Chernoff information rate. An optimal management protects the privacy by minimizing the error exponent of the privacy hypothesis test and meanwhile guarantees the utility hypothesis testing performance by satisfying a lower bound on the corresponding minimal Chernoff information rate. The asymptotic minimum error exponent of the privacy hypothesis test is shown to be characterized by the infimum of corresponding minimal Chernoff information rates subject to the utility guarantees.
引用
收藏
页码:445 / 449
页数:5
相关论文
共 50 条
  • [31] Privacy-Utility Trade-off with the Stratonovich's Value of Information
    Kamatsuka, Akira
    Yoshida, Takahiro
    Matsushima, Toshiyasu
    2021 IEEE INFORMATION THEORY WORKSHOP (ITW), 2021,
  • [32] Privacy-Utility Trade-off of k-subset Mechanism<bold> </bold>
    Zhou, Yihui
    Song, Guangchen
    Liu, Hai
    Lu, Laifeng
    2018 INTERNATIONAL CONFERENCE ON NETWORKING AND NETWORK APPLICATIONS (NANA), 2018, : 212 - 217
  • [33] DRAPE: optimizing private data release under adjustable privacy-utility equilibrium
    Qingyue Xiong
    Qiujun Lan
    Jiaqi Ma
    Huiling Zhou
    Gang Li
    Zheng Yang
    Information Technology and Management, 2024, 25 : 199 - 217
  • [34] Privacy-utility equilibrium data generation based on Wasserstein generative adversarial networks
    Liu, Hai
    Tian, Youliang
    Peng, Changgen
    Wu, Zhenqiang
    INFORMATION SCIENCES, 2023, 642
  • [35] Upper Bound on Privacy-Utility Tradeoff Allowing Positive Excess Distortion Probability
    Saito, Shota
    Matsushima, Toshiyasu
    IEICE TRANSACTIONS ON FUNDAMENTALS OF ELECTRONICS COMMUNICATIONS AND COMPUTER SCIENCES, 2022, E105A (03) : 425 - 427
  • [36] Communicating the Privacy-Utility Trade-off: Supporting Informed Data Donation with Privacy Decision Interfaces for Differential Privacy
    Franzen, Daniel
    Müller-Birn, Claudia
    Wegwarth, Odette
    Proceedings of the ACM on Human-Computer Interaction, 2024, 8 (CSCW1)
  • [37] A Survey on Privacy Preserving Synthetic Data Generation and a Discussion on a Privacy-Utility Trade-off Problem
    Ghatak, Debolina
    Sakurai, Kouichi
    SCIENCE OF CYBER SECURITY, SCISEC 2022 WORKSHOPS, 2022, 1680 : 167 - 180
  • [38] Interpreting Disparate Privacy-Utility Tradeoff in Adversarial Learning via Attribute Correlation
    Zhang, Likun
    Chen, Yahong
    Li, Ang
    Wang, Binghui
    Chen, Yiran
    Li, Fenghua
    Cao, Jin
    Niu, Ben
    2023 IEEE/CVF WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV), 2023, : 4690 - 4698
  • [39] The users' perspective on the privacy-utility trade-offs in health recommender systems
    Valdez, Andre Calero
    Ziefle, Martina
    INTERNATIONAL JOURNAL OF HUMAN-COMPUTER STUDIES, 2019, 121 : 108 - 121
  • [40] On the Privacy-Utility Trade-Off in Differentially Private Hierarchical Text Classification
    Wunderlich, Dominik
    Bernau, Daniel
    Alda, Francesco
    Parra-Arnau, Javier
    Strufe, Thorsten
    APPLIED SCIENCES-BASEL, 2022, 12 (21):