Theoretically principled federated learning for balancing privacy and utility
We propose a general learning framework for the protection mechanisms that protects
privacy via distorting model parameters, which facilitates the trade-off between privacy and …
privacy via distorting model parameters, which facilitates the trade-off between privacy and …
Privacy-preserving federated learning framework based on chained secure multiparty computing
Federated learning (FL) is a promising new technology in the field of IoT intelligence.
However, exchanging model-related data in FL may leak the sensitive information of …
However, exchanging model-related data in FL may leak the sensitive information of …
Privacy-preserving federated learning based on differential privacy and momentum gradient descent
To preserve participants' privacy, Federated Learning (FL) has been proposed to let
participants collaboratively train a global model by sharing their training gradients instead of …
participants collaboratively train a global model by sharing their training gradients instead of …
Regularized mutual learning for personalized federated learning
R Yang, J Tian, Y Zhang - Asian Conference on Machine …, 2021 - proceedings.mlr.press
Federated Learning (FL) is a privacy-protected learning paradigm, which allows many
clients to jointly train a model under the coordination of a server without the local data …
clients to jointly train a model under the coordination of a server without the local data …
A personalized privacy preserving mechanism for crowdsourced federated learning
In this paper, we focus on the privacy preserving mechanism design for crowdsourced
Federated Learning (FL), where a requester can outsource its model training task to some …
Federated Learning (FL), where a requester can outsource its model training task to some …
Model compression and privacy preserving framework for federated learning
Federated learning (FL) as a collaborative learning paradigm has attracted extensive
attention due to its characteristic of privacy preserving, in which the clients train a shared …
attention due to its characteristic of privacy preserving, in which the clients train a shared …
Communication-efficient personalized federated meta-learning in edge networks
Due to the privacy breach risks and data aggregation of traditional centralized machine
learning (ML) approaches, applications, data and computing power are being pushed from …
learning (ML) approaches, applications, data and computing power are being pushed from …
COFEL: Communication-efficient and optimized federated learning with local differential privacy
Federated learning can collaboratively train a global model without gathering clients' private
data. Many works focus on reducing communication cost by designing kinds of client …
data. Many works focus on reducing communication cost by designing kinds of client …
PFLF: Privacy-preserving federated learning framework for edge computing
H Zhou, G Yang, H Dai, G Liu - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Federated learning (FL) can protect clients' privacy from leakage in distributed machine
learning. Applying federated learning to edge computing can protect the privacy of edge …
learning. Applying federated learning to edge computing can protect the privacy of edge …
Clustered federated learning with adaptive local differential privacy on heterogeneous iot data
The Internet of Things (IoT) is penetrating many aspects of our daily life with the proliferation
of artificial intelligence applications. Federated learning (FL) has emerged as a promising …
of artificial intelligence applications. Federated learning (FL) has emerged as a promising …