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
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] Learning Privacy-Preserving Embeddings for Image Data to Be Published
    Li, Chu-Chen
    Li, Cheng-Te
    Lin, Shou-De
    ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY, 2023, 14 (06)
  • [32] Impact of social learning on privacy-preserving data collection
    Akbay A.B.
    Wang W.
    Zhang J.
    Akbay, Abdullah Basar (aakbay@asu.edu), 1600, Institute of Electrical and Electronics Engineers Inc. (02): : 268 - 282
  • [33] Privacy-Preserving Deep Learning on Big Data in Cloud
    Fan, Yongkai
    Zhang, Wanyu
    Bai, Jianrong
    Lei, Xia
    Li, Kuanching
    CHINA COMMUNICATIONS, 2023, 20 (11) : 176 - 186
  • [34] Evaluation of Synthetic Data for Privacy-Preserving Machine Learning
    Hittmeir, Markus
    Ekelhart, Andreas
    Mayer, Rudolf
    ERCIM NEWS, 2020, (123): : 30 - 31
  • [35] Privacy-Preserving Federated Learning Model for Healthcare Data
    Ul Islam, Tanzir
    Ghasemi, Reza
    Mohammed, Noman
    2022 IEEE 12TH ANNUAL COMPUTING AND COMMUNICATION WORKSHOP AND CONFERENCE (CCWC), 2022, : 281 - 287
  • [36] Privacy-Preserving in the Context of Data Mining and Deep Learning
    Altalhi, Amjaad
    Al-Saedi, Maram
    Alsuwat, Hatim
    Alsuwat, Emad
    INTERNATIONAL JOURNAL OF COMPUTER SCIENCE AND NETWORK SECURITY, 2021, 21 (06): : 137 - 142
  • [37] Federated learning scheme for privacy-preserving of medical data
    Bo W.
    Hongtao L.
    Jie W.
    Yina G.
    Xi'an Dianzi Keji Daxue Xuebao/Journal of Xidian University, 2023, 50 (05): : 166 - 177
  • [38] Privacy-preserving machine learning with multiple data providers
    Li, Ping
    Li, Tong
    Ye, Heng
    Li, Jin
    Chen, Xiaofeng
    Xiang, Yang
    FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE, 2018, 87 : 341 - 350
  • [39] Privacy-Preserving Deep Learning on Big Data in Cloud
    Yongkai Fan
    Wanyu Zhang
    Jianrong Bai
    Xia Lei
    Kuanching Li
    China Communications, 2023, 20 (11) : 176 - 186
  • [40] Differential Privacy in Privacy-Preserving Big Data and Learning: Challenge and Opportunity
    Jiang, Honglu
    Gao, Yifeng
    Sarwar, S. M.
    GarzaPerez, Luis
    Robin, Mahmudul
    SILICON VALLEY CYBERSECURITY CONFERENCE, SVCC 2021, 2022, 1536 : 33 - 44