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...
Main Author: | 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.infocomm-journal.com/cjnis/CN/10.11959/j.issn.2096-109x.2018041 |
Similar Items
-
Image Classification Based on Layered Gradient Clipping Under Differential Privacy
by: Chunmei Ma, et al.
Published: (2023-01-01) -
A Communication-Efficient, Privacy-Preserving Federated Learning Algorithm Based on Two-Stage Gradient Pruning and Differentiated Differential Privacy
by: Yong Li, et al.
Published: (2023-11-01) -
Information Privacy Protection Based on Verifiable (t, n)-Threshold Multi-Secret Sharing Scheme
by: Na Wang, et al.
Published: (2020-01-01) -
Multi-Task Learning Using Gradient Balance and Clipping with an Application in Joint Disparity Estimation and Semantic Segmentation
by: Yiyou Guo, et al.
Published: (2022-04-01) -
Consideration of FedProx in Privacy Protection
by: Tianbo An, et al.
Published: (2023-10-01)