Adaptive selection method of differential privacy GAN gradient clipping thresholds
A method of adaptive selection of differential privacy GAN gradient clipping threshold was proposed.The method assumes that a small portion of public data that is identically distributed with the private data can be accessed,a batch of data is randomly selected from the public data,a clipping thresh...
Saved in:
Main Authors: | Peng GUO, Shangping ZHONG, Kaizhi CHEN, Hang CHENG |
---|---|
Format: | Article |
Language: | English |
Published: |
POSTS&TELECOM PRESS Co., LTD
2018-05-01
|
Series: | 网络与信息安全学报 |
Subjects: | |
Online Access: | http://www.cjnis.com.cn/thesisDetails#10.11959/j.issn.2096-109x.2018041 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
Survey of big-data-analysis-resistant privacy protection
by: Wei TONG, et al.
Published: (2016-04-01) -
Federated Learning Based on Kernel Local Differential Privacy and Low Gradient Sampling
by: Yi Chen, et al.
Published: (2025-01-01) -
Dynamic privacy measurement model and evaluation system for mobile edge crowdsensing
by: Mingfeng ZHAO, et al.
Published: (2021-02-01) -
Stochastic gradient descent algorithm preserving differential privacy in MapReduce framework
by: Yihan YU, et al.
Published: (2018-01-01) -
Study on privacy preserving encrypted traffic detection
by: Xinyu ZHANG, et al.
Published: (2021-08-01)