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] Quantifying Privacy Leakage in Graph Embedding
    Duddu, Vasisht
    Boutet, Antoine
    Shejwalkar, Virat
    PROCEEDINGS OF THE 17TH EAI INTERNATIONAL CONFERENCE ON MOBILE AND UBIQUITOUS SYSTEMS: COMPUTING, NETWORKING AND SERVICES (MOBIQUITOUS 2020), 2021, : 76 - 85
  • [2] Quantifying the Information Leakage in Cache Attacks via Symbolic Execution
    Chattopadhyay, Sudipta
    Beck, Moritz
    Rezine, Ahmed
    Zeller, Andreas
    ACM TRANSACTIONS ON EMBEDDED COMPUTING SYSTEMS, 2019, 18 (01)
  • [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] Quantile: Quantifying Information Leakage
    Hadžić V.
    Cassiers G.
    Primas R.
    Mangard S.
    Bloem R.
    IACR Transactions on Cryptographic Hardware and Embedded Systems, 2023, 2024 (01): : 433 - 456
  • [5] 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
  • [6] Quantifying Privacy Leakage in Multi-Agent Planning
    Stolba, Michal
    Tozicka, Jan
    Komenda, Antonin
    ACM TRANSACTIONS ON INTERNET TECHNOLOGY, 2018, 18 (03)
  • [7] Quantifying Location Privacy Leakage from Transaction Prices
    Gervais, Arthur
    Ritzdorf, Hubert
    Lucic, Mario
    Lenders, Vincent
    Capkun, Srdjan
    COMPUTER SECURITY - ESORICS 2016, PT II, 2016, 9879 : 382 - 405
  • [8] Quantifying privacy leakage through answering database queries
    Hsu, TS
    Liau, CJ
    Wang, DW
    Chen, JKP
    INFORMATION SECURITY, PROCEEDINGS, 2002, 2433 : 162 - 176
  • [9] 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
  • [10] Quantifying information leakage in RFID systems
    Huang, Xu
    10TH INTERNATIONAL CONFERENCE ON ADVANCED COMMUNICATION TECHNOLOGY, VOLS I-III: INNOVATIONS TOWARD FUTURE NETWORKS AND SERVICES, 2008, : 84 - 89