Federated Generative Privacy

被引：32
|
作者：
Triastcyn, Aleksei [1 ]
Faltings, Boi [1 ]
机构：
[1] Ecole Polytech Fed Lausanne, Lausanne, Switzerland
来源：
IEEE INTELLIGENT SYSTEMS | 2020年 / 35卷 / 04期
关键词：
Machine learning; Neural nets; Privacy;
D O I：
10.1109/MIS.2020.2993966
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
We propose FedGP, a framework for privacy-preserving data release in the federated learning setting. We use generative adversarial networks, generator components of which are trained by FedAvg algorithm, to draw private artificial data samples and empirically assess the risk of information disclosure. Our experiments show that FedGP is able to generate labeled data of high quality to successfully train and validate supervised models. Finally, we demonstrate that our approach significantly reduces vulnerability of such models to model inversion attacks.
引用
收藏
页码：50 / 57
页数：8
相关论文
共 50 条
  • [31] Efficient Privacy Auditing in Federated Learning
    Chang, Hongyan
    Edwards, Brandon
    Paul, Anindya S.
    Shokri, Reza
    PROCEEDINGS OF THE 33RD USENIX SECURITY SYMPOSIUM, SECURITY 2024, 2024, : 307 - 323
  • [32] Navigating Explainable Privacy in Federated Learning
    Sandeepa, Chamara
    Senevirathna, Thulitha
    Siniarski, Bartlomiej
    Wang, Shen
    Liyanage, Madhusanka
    2024 23RD IFIP NETWORKING CONFERENCE, IFIP NETWORKING 2024, 2024, : 763 - 768
  • [33] Federated Learning with Bayesian Differential Privacy
    Triastcyn, Aleksei
    Faltings, Boi
    2019 IEEE INTERNATIONAL CONFERENCE ON BIG DATA (BIG DATA), 2019, : 2587 - 2596
  • [34] Study of Privacy in Federated Reservoir Computing
    Zawacki, Christopher C.
    Abed, Eyad H.
    2024 58TH ANNUAL CONFERENCE ON INFORMATION SCIENCES AND SYSTEMS, CISS, 2024,
  • [35] Compressed Federated Reinforcement Learning with a Generative Model
    Beikmohammadi, Ali
    Khirirat, Sarit
    Magnusson, Sindri
    MACHINE LEARNING AND KNOWLEDGE DISCOVERY IN DATABASES: RESEARCH TRACK, PT IV, ECML PKDD 2024, 2024, 14944 : 20 - 37
  • [36] Privacy amplification for wireless federated learning with Renyi differential privacy and subsampling
    Tan, Qingjie
    Che, Xujun
    Wu, Shuhui
    Qian, Yaguan
    Tao, Yuanhong
    ELECTRONIC RESEARCH ARCHIVE, 2023, 31 (11): : 7021 - 7039
  • [37] Privacy-Preserving Robust Federated Learning with Distributed Differential Privacy
    Wang, Fayao
    He, Yuanyuan
    Guo, Yunchuan
    Li, Peizhi
    Wei, Xinyu
    2022 IEEE INTERNATIONAL CONFERENCE ON TRUST, SECURITY AND PRIVACY IN COMPUTING AND COMMUNICATIONS, TRUSTCOM, 2022, : 598 - 605
  • [38] Efficient federated learning privacy preservation method with heterogeneous differential privacy
    Ling, Jie
    Zheng, Junchang
    Chen, Jiahui
    COMPUTERS & SECURITY, 2024, 139
  • [39] GuardianAI: Privacy-preserving federated anomaly detection with differential privacy
    Alabdulatif, Abdulatif
    ARRAY, 2025, 26
  • [40] Privacy-preserving federated discovery of DNA motifs with differential privacy
    Chen, Yao
    Gan, Wensheng
    Huang, Gengsen
    Wu, Yongdong
    Yu, Philip S.
    EXPERT SYSTEMS WITH APPLICATIONS, 2024, 249
12345