Knowledge Network Node
Journal of Xidian University. 2023, (04) Core

Efficient deep learning scheme with adaptive differential privacyChinese Full TextEnglish Full Text (MT)

WANG Yuhua;GAO Sheng;ZHU Jianming;HUANG Chen;School of Information, Central University of Finance and Economics;

Abstract: While deep learning has achieved a great success in many fields, it has also gradually exposed a series of serious privacy security issues.As a lightweight privacy protection technology, differential privacy makes the output insensitive to any data in the dataset by adding noise to the model, which is more suitable for the privacy protection of individual users in reality.Aiming at the problems of the dependence of iterations on the privacy budget, low data availability and slow model convergenc... More
Keywords：

deep learning; differential privacy; self-adaptation; privacy loss; model convergence;

  • DOI：

    10.19665/j.issn1001-2400.2023.04.006

  • Series：

    (I) Electronic Technology ＆ Information Science

  • Subject：

    Computer Software and Application of Computer; Automation Technology

  • Classification Code：

    TP309;TP18

Download the mobile appuse the app to scan this coderead the article.

Tips: Please download CAJViewer to view CAJ format full text.

Download: 327 Page: 54-64 Pagecount: 11 Size: 420K

Related Literature
  • Similar Article
  • Reader Recommendation
  • Associated Author