Privacy-Preserving Student Learning with Differentially Private Data-Free Distillation

被引:2
|
作者
Liu, Bochao [1 ,2 ]
Lu, Jianghu [1 ,2 ]
Wang, Pengju [1 ,2 ]
Zhang, Junjie [3 ]
Zeng, Dan [3 ]
Qian, Zhenxing [4 ]
Ge, Shiming [1 ,2 ]
机构
[1] Chinese Acad Sci, Inst Informat Engn, Beijing 100095, Peoples R China
[2] Univ Chinese Acad Sci, Sch Cyber Secur, Beijing 100049, Peoples R China
[3] Shanghai Univ, Sch Commun & Informat Engn, Shanghai 200444, Peoples R China
[4] Fudan Univ, Sch Comp Sci, Shanghai 200433, Peoples R China
来源
2022 IEEE 24TH INTERNATIONAL WORKSHOP ON MULTIMEDIA SIGNAL PROCESSING (MMSP) | 2022年
基金
北京市自然科学基金;
关键词
differential privacy; teacher-student learning; knowledge distillation;
D O I
10.1109/MMSP55362.2022.9950001
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
Deep learning models can achieve high inference accuracy by extracting rich knowledge from massive well-annotated data, but may pose the risk of data privacy leakage in practical deployment. In this paper, we present an effective teacher-student learning approach to train privacy-preserving deep learning models via differentially private data-free distillation. The main idea is generating synthetic data to learn a student that can mimic the ability of a teacher well-trained on private data. In the approach, a generator is first pretrained in a data-free manner by incorporating the teacher as a fixed discriminator. With the generator, massive synthetic data can be generated for model training without exposing data privacy. Then, the synthetic data is fed into the teacher to generate private labels. Towards this end, we propose a label differential privacy algorithm termed selective randomized response to protect the label information. Finally, a student is trained on the synthetic data with the supervision of private labels. In this way, both data privacy and label privacy are well protected in a unified framework, leading to privacy-preserving models. Extensive experiments and analysis clearly demonstrate the effectiveness of our approach.
引用
收藏
页数:6
相关论文
共 50 条
  • [31] Preserving the Privacy of Social Recommendation with a Differentially Private Approach
    Chen, Liang
    Zhu, Peidong
    2015 IEEE INTERNATIONAL CONFERENCE ON SMART CITY/SOCIALCOM/SUSTAINCOM (SMARTCITY), 2015, : 780 - 785
  • [32] Privacy-preserving Deep-learning Models for Fingerprint Data Using Differential Privacy
    Mohammadi, Maryam
    Sabry, Farida
    Labda, Wadha
    Malluhi, Qutaibah
    PROCEEDINGS OF THE 9TH ACM INTERNATIONAL WORKSHOP ON SECURITY AND PRIVACY ANALYTICS, IWSPA 2023, 2023, : 45 - 53
  • [33] Privacy-preserving Deep Learning Models for Law Big Data Feature Learning
    Yuan, Xu
    Zhang, Jianing
    Chen, Zhikui
    Gao, Jing
    Li, Peng
    IEEE 17TH INT CONF ON DEPENDABLE, AUTONOM AND SECURE COMP / IEEE 17TH INT CONF ON PERVAS INTELLIGENCE AND COMP / IEEE 5TH INT CONF ON CLOUD AND BIG DATA COMP / IEEE 4TH CYBER SCIENCE AND TECHNOLOGY CONGRESS (DASC/PICOM/CBDCOM/CYBERSCITECH), 2019, : 128 - 134
  • [34] Dynamic data-free knowledge distillation by easy-to-hard learning strategy
    Li, Jingru
    Zhou, Sheng
    Li, Liangcheng
    Wang, Haishuai
    Bu, Jiajun
    Yu, Zhi
    INFORMATION SCIENCES, 2023, 642
  • [35] Privacy-preserving clustering federated learning for non-IID data
    Luo, Guixun
    Chen, Naiyue
    He, Jiahuan
    Jin, Bingwei
    Zhang, Zhiyuan
    Li, Yidong
    FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE, 2024, 154 : 384 - 395
  • [36] Communication-Efficient and Privacy-Preserving Federated Learning via Joint Knowledge Distillation and Differential Privacy in Bandwidth-Constrained Networks
    Gad, Gad
    Gad, Eyad
    Fadlullah, Zubair Md
    Fouda, Mostafa M.
    Kato, Nei
    IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, 2024, 73 (11) : 17586 - 17601
  • [37] A Privacy-Preserving Federated Learning for Multiparty Data Sharing in Social IoTs
    Yin, Lihua
    Feng, Jiyuan
    Xun, Hao
    Sun, Zhe
    Cheng, Xiaochun
    IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING, 2021, 8 (03): : 2706 - 2718
  • [38] Federated and Privacy-Preserving Learning of Accounting Data in Financial Statement Audits
    Schreyer, Marco
    Sattarov, Timur
    Borth, Damian
    3RD ACM INTERNATIONAL CONFERENCE ON AI IN FINANCE, ICAIF 2022, 2022, : 105 - 113
  • [39] ROBUSTNESS AND DIVERSITY SEEKING DATA-FREE KNOWLEDGE DISTILLATION
    Han, Pengchao
    Park, Jihong
    Wang, Shiqiang
    Liu, Yejun
    2021 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP 2021), 2021, : 2740 - 2744
  • [40] Data-free knowledge distillation in neural networks for regression
    Kang, Myeonginn
    Kang, Seokho
    EXPERT SYSTEMS WITH APPLICATIONS, 2021, 175