Model split-based data privacy protection method for federated learning
Split learning (SL) enables data privacy preservation by allowing clients to collaboratively train a deep learning model with the server without sharing raw data. However, the SL still has limitations such as potential data privacy leakage. Therefore, binarized split learning-based data privacy prot...
Saved in:
Main Author: | CHEN Ka |
---|---|
Format: | Article |
Language: | zho |
Published: |
Beijing Xintong Media Co., Ltd
2024-09-01
|
Series: | Dianxin kexue |
Subjects: | |
Online Access: | http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2024206/ |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
Multi-Task Federated Split Learning Across Multi-Modal Data with Privacy Preservation
by: Yipeng Dong, et al.
Published: (2025-01-01) -
Survey of split learning data privacy
by: QIN Yiqun, et al.
Published: (2024-06-01) -
Privacy-enhanced federated learning scheme based on generative adversarial networks
by: Feng YU, et al.
Published: (2023-06-01) -
Survey of artificial intelligence data security and privacy protection
by: Kui REN, et al.
Published: (2021-02-01) -
Balancing Privacy and Utility in Split Learning: An Adversarial Channel Pruning-Based Approach
by: Afnan Alhindi, et al.
Published: (2025-01-01)