FedCVG: a two-stage robust federated learning optimization algorithm
Abstract Federated learning provides an effective solution to the data privacy issue in distributed machine learning. However, distributed federated learning systems are inherently susceptible to data poisoning attacks and data heterogeneity. Under conditions of high data heterogeneity, the gradient...
Saved in:
| Main Authors: | Runze Zhang, Yang Zhang, Yating Zhao, Bin Jia, Wenjuan Lian |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-05-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-02722-4 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
An Optimal Two-Step Approach for Defense Against Poisoning Attacks in Federated Learning
by: Yasir Ali, et al.
Published: (2025-01-01) -
AIDFL: An Information-Driven Anomaly Detector for Data Poisoning in Decentralized Federated Learning
by: Xiao Chen, et al.
Published: (2025-01-01) -
BPS-FL: Blockchain-Based Privacy-Preserving and Secure Federated Learning
by: Jianping Yu, et al.
Published: (2025-02-01) -
Robust-PFedproto: robust federated prototype learning based on personalized layers
by: XU Mingdi, et al.
Published: (2025-06-01) -
FedHSP: A Robust Federated Learning Framework Coherently Addressing Heterogeneity, Security, and Performance Challenges
by: Divya G. Nair, et al.
Published: (2025-01-01)