A Survey of Privacy-Preserving Techniques in Federated Graph Neural Networks

Lingyu Wang

doi:10.47297/taposatWSP2633-456910.20250606

PDF
Export
Share
Collection
Album

A Survey of Privacy-Preserving Techniques in Federated Graph Neural Networks

Volume 6, Issue 6

Views: 0 Downloads: 0

A Survey of Privacy-Preserving Techniques in Federated Graph Neural Networks
A Survey of Privacy-Preserving Techniques in Federated Graph Neural Networks
School of Arts and Sciences, China University of Petroleum-Beijing at Karamay, Karamay, Xinjiang, 834000, China
Vol. 6, Issue 6, Pages: 49-54(2025)
Published：30 June 2025
DOI：10.47297/taposatWSP2633-456910.20250606
Accepted：

Scan QR Code

Wang Lingyu.A Survey of Privacy-Preserving Techniques in Federated Graph Neural Networks[J].Theory and Practice of Science and Technology,2025,06(06):49-54.
DOI：

Wang Lingyu.A Survey of Privacy-Preserving Techniques in Federated Graph Neural Networks[J].Theory and Practice of Science and Technology,2025,06(06):49-54. DOI： 10.47297/taposatWSP2633-456910.20250606.

摘要

Abstract

Federated Graph Neural Networks (FedGNNs) are increasingly adopted in high-sensitivity domains—such as finance

healthcare

and government—imposing stringent requirements on privacy

performance

and communication efficiency. This survey systematically reviews four core privacy-preserving techniques (homomorphic encryption

differential privacy

secure multi-party computation

and trusted execution environments) and introduces an evaluation framework that balances privacy

performance

and efficiency. Within this framework

we compare encryption-based aggregation

embedding perturbation

graph-structure anonymization

uncertainty-aware distillation

and decentralized optimization. To handle dynamic graphs and multimodal data

we propose a sliding-window temporal encoding and cross-modal alignment strategy

and design a spatiotemporal multimodal defense pipeline with adaptive aggregation and privacy-budget scheduling for robust

efficient protection. Finally

we identify future challenges—standardized evaluation

adversarial-defense benchmarks

and industrial deployment—and outline design principles to guide secure FedGNN implementations in sensitive environments.

关键词

Keywords

references

Zhang, Z., & Li, H. (2024). A comprehensive survey on trustworthy graph neural networks.

Li, W., & Wang, M. (2024). A survey on federated graph neural networks: Methods and applications.

Chen, Y., & Zhao, L. (2024). FedPerGNN: Privacy-preserving personalized recommendation via federated graph neural networks.

Wu, X., & Zhou, Y. (2023). Vertically federated graph neural network for privacy-preserving node classification.

Chen, Q., & Sun, R. (2023). BI-FedGNN: Bayesian inference based federated GNN with privacy-aware uncertainty quantification.

Wang, L., & Liu, Y. (2023). MDD-Fed: Multi-defense distillation based federated GNN against backdoor attack.

Liu, F., & Zhang, L. (2023). A survey on privacy-preserving techniques in federated graph neural networks.

Zhao, M., & Yang, C. (2023). A survey of privacy protection technologies in federated learning.

Zhang, H., & Zhou, Q. (2022). FedPerGNN: A privacy-preserving personalized federated graph neural network framework.

Zhu, L., & Wang, X. (2023). Isomorphic federated graph neural network for privacy-preserved supply chain data sharing.

Cheng, F. (2024). Research and application of federated graph neural network models.

Sun, M., & Liu, J. (2023). Isomorphic federated graph neural network.

He, K., & Zhang, L. (2022). Federated graph neural network for privacy-preserving recommendation.

Alert me when the article has been cited

Submit

No data

Related Author

No data

Related Institution

No data

⁰