Security of federated learning for cloud-edge intelligence collaborative computing

Jie Yang, Jun Zheng, Zheng Zhang, Q. I. Chen, Duncan S. Wong, Yuanzhang Li*

*此作品的通讯作者

科研成果: 期刊稿件文章同行评审

19 引用 (Scopus)

摘要

Federated Learning (FL) is one of the key technologies to solve privacy protection for cloud-edge intelligent collaborative computing, and its security and privacy issues have attracted extensive attention from academia and industry. FL is a distributed privacy protection framework. Multiple edged nodes or servers jointly train a machine learning model by sharing model parameters without exchanging local data. However, there are still many security risks and privacy threats in FL in edge-cloud collaborative computing. In this paper, we mainly discuss the security and privacy challenges on FL in collaborative computing at the edge. First, we introduce the principle, classification, and threat model of FL in edge-cloud collaboration, which helps understand the challenges faced by edge-cloud collaborative computing. Second, privacy leakage attacks and poisoning attacks launched by adversaries or honest but curious actors are summarized and compared. Then, the problems existing on the attack method are summarized and analyzed. Finally, the future development direction of FL in the field of edge-cloud collaborative computing is further discussed.

源语言英语
页(从-至)9290-9308
页数19
期刊International Journal of Intelligent Systems
37
11
DOI
出版状态已出版 - 11月 2022

指纹

探究 'Security of federated learning for cloud-edge intelligence collaborative computing' 的科研主题。它们共同构成独一无二的指纹。

引用此

Yang, J., Zheng, J., Zhang, Z., Chen, Q. I., Wong, D. S., & Li, Y. (2022). Security of federated learning for cloud-edge intelligence collaborative computing. International Journal of Intelligent Systems, 37(11), 9290-9308. https://doi.org/10.1002/int.22992