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 Web-Search Privacy
    Gervais, Arthur
    Shokri, Reza
    Singla, Adish
    Capkun, Srdjan
    Lenders, Vincent
    CCS'14: PROCEEDINGS OF THE 21ST ACM CONFERENCE ON COMPUTER AND COMMUNICATIONS SECURITY, 2014, : 966 - 977
  • [22] Quantifying the Vulnerability of Attributes for Effective Privacy Preservation Using Machine Learning
    Majeed, Abdul
    Hwang, Seong Oun
    IEEE ACCESS, 2023, 11 : 4400 - 4411
  • [23] Gotcha! This Model Uses My Code! Evaluating Membership Leakage Risks in Code Models
    Yang, Zhou
    Zhao, Zhipeng
    Wang, Chenyu
    Shi, Jieke
    Kim, Dongsun
    Han, Donggyun
    Lo, David
    IEEE TRANSACTIONS ON SOFTWARE ENGINEERING, 2024, 50 (12) : 3290 - 3306
  • [24] Secure Inference via Deep Learning as a Service without Privacy Leakage
    Anh-Tu Tran
    The-Dung Luong
    Cong-Chieu Ha
    Duc-Tho Hoang
    Thi-Luong Tran
    2021 RIVF INTERNATIONAL CONFERENCE ON COMPUTING AND COMMUNICATION TECHNOLOGIES (RIVF 2021), 2021, : 267 - 272
  • [25] Preserving Privacy in GANs Against Membership Inference Attack
    Shateri, Mohammadhadi
    Messina, Francisco
    Labeau, Fabrice
    Piantanida, Pablo
    IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2024, 19 : 1728 - 1743
  • [26] MagSpy: Revealing User Privacy Leakage via Magnetometer on Mobile Devices
    Fu, Yongjian
    Yang, Lanqing
    Pan, Hao
    Chen, Yi-Chao
    Xue, Guangtao
    Ren, Ju
    IEEE TRANSACTIONS ON MOBILE COMPUTING, 2025, 24 (03) : 2455 - 2469
  • [27] Privacy Preserving Smart Meter Streaming Against Information Leakage of Appliance Status
    Hong, Yuan
    Liu, Wen Ming
    Wang, Lingyu
    IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2017, 12 (09) : 2227 - 2241
  • [28] Context-Aware Local Information Privacy
    Jiang, Bo
    Seif, Mohamed
    Tandon, Ravi
    Li, Ming
    IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2021, 16 : 3694 - 3708
  • [29] A Novel User Membership Leakage Attack in Collaborative Deep Learning
    Mao, Yaoru
    Zhu, Xiaoyan
    Zheng, Wenbin
    Yuan, Danni
    Ma, Jianfeng
    2019 11TH INTERNATIONAL CONFERENCE ON WIRELESS COMMUNICATIONS AND SIGNAL PROCESSING (WCSP), 2019,
  • [30] Exploring the Relationship Between Privacy and Utility in Mobile Health: Algorithm Development and Validation via Simulations of Federated Learning, Differential Privacy, and External Attacks
    Shen, Alexander
    Francisco, Luke
    Sen, Srijan
    Tewari, Ambuj
    JOURNAL OF MEDICAL INTERNET RESEARCH, 2023, 25