IDEAS home Printed from https://ideas.repec.org/a/gam/jmathe/v11y2023i2p330-d1029082.html
   My bibliography  Save this article

Adaptive Differential Privacy Mechanism Based on Entropy Theory for Preserving Deep Neural Networks

Author

Listed:
  • Xiangfei Zhang

    (School of Cyberspace Security, Hainan University, Haikou 570228, China)

  • Feng Yang

    (School of Computer Science and Technology, Hainan University, Haikou 570228, China)

  • Yu Guo

    (School of Computer Science and Technology, Hainan University, Haikou 570228, China)

  • Hang Yu

    (School of Computer Science and Technology, Hainan University, Haikou 570228, China)

  • Zhengxia Wang

    (School of Computer Science and Technology, Hainan University, Haikou 570228, China)

  • Qingchen Zhang

    (School of Computer Science and Technology, Hainan University, Haikou 570228, China)

Abstract

Recently, deep neural networks (DNNs) have achieved exciting things in many fields. However, the DNN models have been proven to divulge privacy, so it is imperative to protect the private information of the models. Differential privacy is a promising method to provide privacy protection for DNNs. However, existing DNN models based on differential privacy protection usually inject the same level of noise into parameters, which may lead to a balance between model performance and privacy protection. In this paper, we propose an adaptive differential privacy scheme based on entropy theory for training DNNs, with the aim of giving consideration to the model performance and protecting the private information in the training data. The proposed scheme perturbs the gradients according to the information gain of neurons during training, that is, in the process of back propagation, less noise is added to neurons with larger information gain, and vice-versa. Rigorous experiments conducted on two real datasets demonstrate that the proposed scheme is highly effective and outperforms existing solutions.

Suggested Citation

  • Xiangfei Zhang & Feng Yang & Yu Guo & Hang Yu & Zhengxia Wang & Qingchen Zhang, 2023. "Adaptive Differential Privacy Mechanism Based on Entropy Theory for Preserving Deep Neural Networks," Mathematics, MDPI, vol. 11(2), pages 1-11, January.
  • Handle: RePEc:gam:jmathe:v:11:y:2023:i:2:p:330-:d:1029082
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/2227-7390/11/2/330/pdf
    Download Restriction: no

    File URL: https://www.mdpi.com/2227-7390/11/2/330/
    Download Restriction: no
    ---><---

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Yun Tan & Changshu Zhan & Youchun Pi & Chunhui Zhang & Jinghui Song & Yan Chen & Amir-Mohammad Golmohammadi, 2023. "A Hybrid Algorithm Based on Social Engineering and Artificial Neural Network for Fault Warning Detection in Hydraulic Turbines," Mathematics, MDPI, vol. 11(10), pages 1-18, May.

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:gam:jmathe:v:11:y:2023:i:2:p:330-:d:1029082. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    We have no bibliographic references for this item. You can help adding them by using this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: MDPI Indexing Manager (email available below). General contact details of provider: https://www.mdpi.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.