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
  • [1] 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
  • [2] 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
  • [3] Mosaic: Quantifying Privacy Leakage in Mobile Networks
    Xia, Ning
    Song, Han Hee
    Liao, Yong
    Iliofotou, Marios
    Nucci, Antonio
    Zhang, Zhi-Li
    Kuzmanovic, Aleksandar
    ACM SIGCOMM COMPUTER COMMUNICATION REVIEW, 2013, 43 (04) : 279 - 290
  • [4] GANobfuscator: Mitigating Information Leakage Under GAN via Differential Privacy
    Xu, Chugui
    Ren, Ju
    Zhang, Deyu
    Zhang, Yaoxue
    Qin, Zhan
    Ren, Kui
    IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2019, 14 (09) : 2358 - 2371
  • [5] VeriDIP: Verifying Ownership of Deep Neural Networks Through Privacy Leakage Fingerprints
    Hu, Aoting
    Lu, Zhigang
    Xie, Renjie
    Xue, Minhui
    IEEE TRANSACTIONS ON DEPENDABLE AND SECURE COMPUTING, 2024, 21 (04) : 2568 - 2584
  • [6] Systematically Quantifying IoT Privacy Leakage in Mobile Networks
    Hui, Shuodi
    Wang, Zhenhua
    Hou, Xueshi
    Wang, Xiao
    Wang, Huandong
    Li, Yong
    Jin, Depeng
    IEEE INTERNET OF THINGS JOURNAL, 2021, 8 (09) : 7115 - 7125
  • [7] Quantifying privacy leakage through answering database queries
    Hsu, TS
    Liau, CJ
    Wang, DW
    Chen, JKP
    INFORMATION SECURITY, PROCEEDINGS, 2002, 2433 : 162 - 176
  • [8] Quantifying Source Location Privacy Routing Performance via Divergence and Information Loss
    Bradbury, Matthew
    Jhumka, Arshad
    IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2022, 17 : 3890 - 3905
  • [9] Quantifying Temporal Privacy Leakage in Continuous Event Data Publishing
    Rafiei, Majid
    Elkoumy, Gamal
    Van der Aalst, Wil M. P.
    COOPERATIVE INFORMATION SYSTEMS (COOPIS 2022), 2022, 13591 : 75 - 94
  • [10] A Graph Symmetrization Bound on Channel Information Leakage Under Blowfish Privacy
    Edwards, Tobias
    Rubinstein, Benjamin I. P.
    Zhang, Zuhe
    Zhou, Sanming
    IEEE TRANSACTIONS ON INFORMATION THEORY, 2022, 68 (01) : 538 - 548