LHKV: A Key-Value Data Collection Mechanism Under Local Differential Privacy

被引:0
作者
Xue, Weihao [1 ]
Sang, Yingpeng [1 ]
Tian, Hui [2 ]
机构
[1] Sun Yat Sen Univ, Sch Comp Sci & Engn, Guangzhou, Peoples R China
[2] Griffith Univ, Sch Informat & Commun Technol, Nathan, Qld, Australia
来源
DATABASE AND EXPERT SYSTEMS APPLICATIONS, DEXA 2023, PT I | 2023年 / 14146卷
关键词
Local differential privacy; Key-value data; Local hashing;
D O I
10.1007/978-3-031-39847-6_16
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
Local differential privacy (LDP) is an emerging technology used to protect privacy. Users are required to locally perturb their raw data under the framework of LDP, before they are transmitted to the server. This technology can be applied to various data types, including key-value data. However, in existing LDP mechanisms for key-value data, it is difficult to balance data utility and communication costs, particularly when the domain of keys is large. In this paper we propose a local-hashing-based mechanism called LHKV for collecting key-value data. LHKV can maintain high utility and keep the end-to-end communication costs low. We provide theoretical proof that LHKV satisfies epsilon-LDP and analyze the variances of frequency and mean estimations. Moreover, we employ Fast Local Hashing to accelerate the aggregation and estimation process, which significantly reduces computation costs. We also conduct experiments to demonstrate that, in comparison with the existing mechanisms, LHKV can effectively reduce communication costs without sacrificing utility while ensuring the same LDP guarantees.
引用
收藏
页码:228 / 242
页数:15
相关论文
共 50 条
  • [31] Continuous Release of Data Streams under both Centralized and Local Differential Privacy
    Wang, Tianhao
    Chen, Joann Qiongna
    Zhang, Zhikun
    Su, Dong
    Cheng, Yueqiang
    Li, Zhou
    Li, Ninghui
    Jha, Somesh
    CCS '21: PROCEEDINGS OF THE 2021 ACM SIGSAC CONFERENCE ON COMPUTER AND COMMUNICATIONS SECURITY, 2021, : 1237 - 1253
  • [32] Privacy preserving classification on local differential privacy in data centers
    Fan, Weibei
    He, Jing
    Guo, Mengjiao
    Li, Peng
    Han, Zhijie
    Wang, Ruchuan
    JOURNAL OF PARALLEL AND DISTRIBUTED COMPUTING, 2020, 135 (135) : 70 - 82
  • [33] Oblivious Statistic Collection With Local Differential Privacy in Mutual Distrust
    Sasada, Taisho
    Taenaka, Yuzo
    Kadobayashi, Youki
    IEEE ACCESS, 2023, 11 : 21374 - 21386
  • [34] Fisher information under local differential privacy
    Barnes L.P.
    Chen W.-N.
    Özgür A.
    IEEE Journal on Selected Areas in Information Theory, 2020, 1 (03): : 645 - 659
  • [35] Learning Markov Chain Models from Sequential Data Under Local Differential Privacy
    Guner, Efehan
    Gursoy, M. Emre
    COMPUTER SECURITY - ESORICS 2023, PT II, 2024, 14345 : 359 - 379
  • [36] Mean Estimation of Numerical Data Under (∈, δ)-Utility-Optimized Local Differential Privacy
    Zhang, Yue
    Zhu, Youwen
    Wang, Shaowei
    Huang, Xiaohua
    IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2024, 19 : 9656 - 9669
  • [37] Personalized sampling graph collection with local differential privacy for link prediction
    Jiang, Linyu
    Yan, Yukun
    Tian, Zhihong
    Xiong, Zuobin
    Han, Qilong
    WORLD WIDE WEB-INTERNET AND WEB INFORMATION SYSTEMS, 2023, 26 (05): : 2669 - 2689
  • [38] Personalized sampling graph collection with local differential privacy for link prediction
    Linyu Jiang
    Yukun Yan
    Zhihong Tian
    Zuobin Xiong
    Qilong Han
    World Wide Web, 2023, 26 : 2669 - 2689
  • [39] A Privacy-Preserving Mechanism Based on Local Differential Privacy in Edge Computing
    Bi, Mengnan
    Wang, Yingjie
    Cai, Zhipeng
    Tong, Xiangrong
    CHINA COMMUNICATIONS, 2020, 17 (09) : 50 - 65
  • [40] Collecting Individual Trajectories under Local Differential Privacy
    Yang, Jianyu
    Cheng, Xiang
    Su, Sen
    Sun, Huizhong
    Chen, Changju
    2022 23RD IEEE INTERNATIONAL CONFERENCE ON MOBILE DATA MANAGEMENT (MDM 2022), 2022, : 99 - 108