Insuring against the perils in distributed learning: privacy-preserving empirical risk minimization

Insuring against the perils in distributed learning: privacy-preserving empirical risk minimization

Multiple organizations would benefit from collaborative learning models trained over aggregated datasets from various human activity recognition applications without privacy leakages. Two of the prevailing privacy-preserving protocols, secure multi-party computation and differential privacy, however...

Full description

Bibliographic Details
Main Authors: Kwabena Owusu-Agyemang, Zhen Qin, Appiah Benjamin, Hu Xiong, Zhiguang Qin
Format: Article
Language:English
Published: AIMS Press 2021-04-01
Series:Mathematical Biosciences and Engineering
Subjects:
internet of things
differential privacy
fully homomorphic encryption
privacy-preserving
secure multi-party computations
human activity recognition
Online Access:https://www.aimspress.com/article/doi/10.3934/mbe.2021151?viewType=HTML

Internet

https://www.aimspress.com/article/doi/10.3934/mbe.2021151?viewType=HTML

Similar Items