CoChat

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

Open access

The DOI matches its Crossref record; 38 of the 38 references it cites were found in a registry or an index.

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.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.3390/math11020330

Cites

38 of 38 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1 Comparison of the privacy budget ratio between ADPPL and EnADPP.
Figure 1 Comparison of the privacy budget ratio between ADPPL and EnADPP.CC-BY · From the PDF

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Cited by

See all 24

Metadata

Authors
Zhang, X., Yang, F., Guo, Y., Yu, H., Wang, Z., & Zhang, Q.
Affiliations
Hainan University (CN)
Corresponding author
Zhang, Qingchen
Venue
Mathematics
Publisher
MDPI AG
Published
2023-01-08
Volume
11
Issue
2
Pages
330
ISSN
2227-7390 (ISSN-L)
OpenAlex
W4313890081
Cited by
24
References
38
Citations by year
2026: 4 · 2025: 10 · 2024: 4 · 2023: 6
FWCI
2.12
Type
journal article
Language
en
Open access
Locations
  • Mathematics (publishedVersion, cc-by)
  • RePEc: Research Papers in Economics (submittedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
  • Major Science and Technology Plan of Hainan (ZDKJ2021016, ZDYF2021GXJS017, ZDYF2021GXJS016, 6216070295, 82160345, 2021-016)
  • Key Research and Development Project of Hainan Province (ZDKJ2021016, ZDYF2021GXJS017, ZDYF2021GXJS016, 6216070295, 82160345, 2021-016)
  • National Natural Science Foundation of China (ZDKJ2021016, ZDYF2021GXJS017, ZDYF2021GXJS016, 6216070295, 82160345, 2021-016)
  • Key Science and Technology Plan Project of Haikou (ZDKJ2021016, ZDYF2021GXJS017, ZDYF2021GXJS016, 6216070295, 82160345, 2021-016)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
  • Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
  • Physical Sciences › Computer Science › Computer Networks and Communications › Cryptography and Data Security
Keywords
differential privacy, deep neural network, entropy theory, gradient perturbation, privacy-preserving machine learning, model privacy

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.