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
  • [1] Data-Free Knowledge Distillation for Privacy-Preserving Efficient UAV Networks
    Yu, Guyang
    2022 6TH INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION SCIENCES (ICRAS 2022), 2022, : 52 - 56
  • [2] Model Conversion via Differentially Private Data-Free Distillation
    Liu, Bochao
    Wang, Pengju
    Li, Shikun
    Zeng, Dan
    Ge, Shiming
    PROCEEDINGS OF THE THIRTY-SECOND INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, IJCAI 2023, 2023, : 2187 - 2195
  • [3] Privacy-Preserving Federated Learning with Differentially Private Hyperdimensional Computing
    Piran, Fardin Jalil
    Chen, Zhiling
    Imani, Mohsen
    Imani, Farhad
    COMPUTERS & ELECTRICAL ENGINEERING, 2025, 123
  • [4] Learning Privacy-Preserving Student Networks via Discriminative-Generative Distillation
    Ge, Shiming
    Liu, Bochao
    Wang, Pengju
    Li, Yong
    Zeng, Dan
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2023, 32 : 116 - 127
  • [5] Differentially Private Normalizing Flows for Privacy-Preserving Density Estimation
    Waites, Chris
    Cummings, Rachel
    AIES '21: PROCEEDINGS OF THE 2021 AAAI/ACM CONFERENCE ON AI, ETHICS, AND SOCIETY, 2021, : 1000 - 1009
  • [6] Privacy-Preserving Genomic Data Publishing via Differentially-Private Suffix Tree
    Khatri, Tanya
    Dagher, Gaby G.
    Hou, Yantian
    SECURITY AND PRIVACY IN COMMUNICATION NETWORKS, SECURECOMM, PT I, 2019, 304 : 569 - 584
  • [7] Data-Free Learning of Student Networks
    Chen, Hanting
    Wang, Yunhe
    Xu, Chang
    Yang, Zhaohui
    Liu, Chuanjian
    Shi, Boxin
    Xu, Chunjing
    Xu, Chao
    Tian, Qi
    2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019), 2019, : 3513 - 3521
  • [8] Ensemble Attention Distillation for Privacy-Preserving Federated Learning
    Gong, Xuan
    Sharma, Abhishek
    Karanam, Srikrishna
    Wu, Ziyan
    Chen, Terrence
    Doermann, David
    Innanje, Arun
    2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021), 2021, : 15056 - 15066
  • [9] Federated Learning With Privacy-Preserving Ensemble Attention Distillation
    Gong, Xuan
    Song, Liangchen
    Vedula, Rishi
    Sharma, Abhishek
    Zheng, Meng
    Planche, Benjamin
    Innanje, Arun
    Chen, Terrence
    Yuan, Junsong
    Doermann, David
    Wu, Ziyan
    IEEE TRANSACTIONS ON MEDICAL IMAGING, 2023, 42 (07) : 2057 - 2067
  • [10] Privacy preserving classification over differentially private data
    Zorarpaci, Ezgi
    Ozel, Selma Ayse
    WILEY INTERDISCIPLINARY REVIEWS-DATA MINING AND KNOWLEDGE DISCOVERY, 2021, 11 (03)