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
  • [31] Cumulant Expansion of Mutual Information for Quantifying Leakage of a Protected Secret
    Rioul, Olivier
    Cheng, Wei
    Guilley, Sylvain
    2021 IEEE INTERNATIONAL SYMPOSIUM ON INFORMATION THEORY (ISIT), 2021, : 2596 - 2601
  • [32] An Analysis Framework for Information Loss and Privacy Leakage on Android Applications
    Yeh, Kuo-Hui
    Lo, Nai-Wei
    Fan, Chuan-Yen
    2014 IEEE 3RD GLOBAL CONFERENCE ON CONSUMER ELECTRONICS (GCCE), 2014, : 216 - 218
  • [33] Quantifying the Effect of Co-location Information on Location Privacy
    Olteanu, Alexandra-Mihaela
    Huguenin, Kevin
    Shokri, Reza
    Hubaux, Jean-Pierre
    PRIVACY ENHANCING TECHNOLOGIES, PETS 2014, 2014, 8555 : 184 - 203
  • [34] Using Renyi-divergence and Arimoto-Renyi Information to Quantify Membership Information Leakage
    Farokhi, Farhad
    2021 55TH ANNUAL CONFERENCE ON INFORMATION SCIENCES AND SYSTEMS (CISS), 2021,
  • [35] Secure Decentralized Aggregation to Prevent Membership Privacy Leakage in Edge-Based Federated Learning
    Shen, Meng
    Wang, Jing
    Zhang, Jie
    Zhao, Qinglin
    Peng, Bohan
    Wu, Tong
    Zhu, Liehuang
    Xu, Ke
    IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING, 2024, 11 (03): : 3105 - 3119
  • [36] Unifying Privacy Measures via Maximal (α, β)-Leakage (MαbeL)
    Gilani, Atefeh
    Kurri, Gowtham R.
    Kosut, Oliver
    Sankar, Lalitha
    IEEE TRANSACTIONS ON INFORMATION THEORY, 2024, 70 (06) : 4368 - 4395
  • [37] Privacy Leakage via Attribute Inference in Directed Social Networks
    Wong, Raymond K.
    Vidyalakshmi, B. S.
    INFORMATION AND COMMUNICATIONS SECURITY, ICICS 2016, 2016, 9977 : 333 - 346
  • [38] Variations and Extensions of Information Leakage Metrics with Applications to Privacy Problems with Imperfect Statistical Information
    Sakib, Shahnewaz Karim
    Amariucai, George T.
    Guan, Yong
    2023 IEEE 36TH COMPUTER SECURITY FOUNDATIONS SYMPOSIUM, CSF, 2023, : 407 - 422
  • [39] Tunable Measures for Information Leakage and Applications to Privacy-Utility Tradeoffs
    Liao, Jiachun
    Kosut, Oliver
    Sankar, Lalitha
    Calmon, Flavio du Pin
    IEEE TRANSACTIONS ON INFORMATION THEORY, 2019, 65 (12) : 8043 - 8066
  • [40] An approach for prevention of privacy breach and information leakage in sensitive data mining
    Prakash, M.
    Singaravel, G.
    COMPUTERS & ELECTRICAL ENGINEERING, 2015, 45 : 134 - 140