Quantifying Membership Privacy via Information Leakage

被引:17
|
作者
Saeidian, Sara [1 ]
Cervia, Giulia [2 ,3 ]
Oechtering, Tobias J. [1 ]
Skoglund, Mikael [1 ]
机构
[1] KTH Royal Inst Technol, Div Informat Sci & Engn, Sch Elect Engn & Comp Sci, S-10044 Stockholm, Sweden
[2] KTH Royal Inst Technol, Sch Elect Engn & Comp Sci, S-10044 Stockholm, Sweden
[3] Univ Lille, Ctr Digital Syst, IMT Lille Douai, Inst Mines Telecom, F-59000 Lille, France
关键词
Privacy; Differential privacy; Measurement; Training; Machine learning; Data models; Upper bound; Privacy-preserving machine learning; membership inference; maximal leakage; log-concave probability density;
D O I
10.1109/TIFS.2021.3073804
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
Machine learning models are known to memorize the unique properties of individual data points in a training set. This memorization capability can be exploited by several types of attacks to infer information about the training data, most notably, membership inference attacks. In this paper, we propose an approach based on information leakage for guaranteeing membership privacy. Specifically, we propose to use a conditional form of the notion of maximal leakage to quantify the information leaking about individual data entries in a dataset, i.e., the entrywise information leakage. We apply our privacy analysis to the Private Aggregation of Teacher Ensembles (PATE) framework for privacy-preserving classification of sensitive data and prove that the entrywise information leakage of its aggregation mechanism is Schur-concave when the injected noise has a log-concave probability density. The Schur-concavity of this leakage implies that increased consensus among teachers in labeling a query reduces its associated privacy cost. Finally, we derive upper bounds on the entrywise information leakage when the aggregation mechanism uses Laplace distributed noise.
引用
收藏
页码:3096 / 3108
页数:13
相关论文
共 50 条
  • [21] Quantifying Information Leakage in Finite Order Deterministic Programs
    Zhu, Ji
    Srivatsa, Mudhakar
    2011 IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS (ICC), 2011,
  • [22] Quantifying Information Leakage for Security Verification of Compiler Optimizations
    Panigrahi, Priyanka
    Paul, Abhik
    Karfa, Chandan
    IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS, 2022, 41 (11) : 4385 - 4396
  • [23] Quantifying Information Leakage in a Processor Caused by the Execution of Instructions
    Yilmaz, Baki Berkay
    Callan, Robert
    Prvulovic, Milos
    Zajic, Alenka
    MILCOM 2017 - 2017 IEEE MILITARY COMMUNICATIONS CONFERENCE (MILCOM), 2017, : 255 - 260
  • [24] A Unified Framework of Graph Information Bottleneck for Robustness and Membership Privacy
    Dai, Enyan
    Cui, Limeng
    Wang, Zhengyang
    Tang, Xianfeng
    Wang, Yinghan
    Cheng, Monica
    Yin, Bing
    Wang, Suhang
    PROCEEDINGS OF THE 29TH ACM SIGKDD CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING, KDD 2023, 2023, : 368 - 379
  • [25] Information Leakage Metrics for Adversaries with Incomplete Information: Binary Privacy Mechanism
    Sakib, Shahnewaz Karim
    Amariucai, George T.
    Guan, Yong
    IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS (ICC 2021), 2021,
  • [26] Privacy Preserving Machine Learning with Limited Information Leakage
    Tang, Wenyi
    Qin, Bo
    Zhao, Suyun
    Zhao, Boning
    Xue, Yunzhi
    Chen, Hong
    NETWORK AND SYSTEM SECURITY, NSS 2019, 2019, 11928 : 352 - 370
  • [27] A Quantifying Metric for Privacy Protection Based on Information Theory
    Gao, Feng
    He, Jingsha
    Peng, Shufen
    Wu, Xu
    2010 THIRD INTERNATIONAL SYMPOSIUM ON INTELLIGENT INFORMATION TECHNOLOGY AND SECURITY INFORMATICS (IITSI 2010), 2010, : 216 - 220
  • [28] Beyond Model-Level Membership Privacy Leakage: an Adversarial Approach in Federated Learning
    Chen, Jiale
    Zhang, Jiale
    Zhao, Yanchao
    Han, Hao
    Zhu, Kun
    Chen, Bing
    2020 29TH INTERNATIONAL CONFERENCE ON COMPUTER COMMUNICATIONS AND NETWORKS (ICCCN 2020), 2020,
  • [29] Measures of Information Leakage for Incomplete Statistical Information: Application to a Binary Privacy Mechanism
    Sakib, Shahnewaz Karim
    Amariucai, George T.
    Guan, Yong
    ACM TRANSACTIONS ON PRIVACY AND SECURITY, 2023, 26 (04)
  • [30] Quantifying Information Leakage Using Model Counting Constraint Solvers
    Bultan, Tevfik
    VERIFIED SOFTWARE: THEORIES, TOOLS, AND EXPERIMENTS, VSTTE 2019, 2020, 12031 : 30 - 35