Towards efficient asynchronous federated learning in heterogeneous edge environments

Y Zhou, X Pang, Z Wang, J Hu, P Sun… - IEEE INFOCOM 2024 …, 2024 - ieeexplore.ieee.org
Federated learning (FL) is widely used in edge environments as a privacy-preserving
collaborative learning paradigm. However, edge devices often have heterogeneous …

PPMM-DA: privacy-preserving multi-dimensional and multi-subset data aggregation with differential privacy for fog-based smart grids

S Zhao, S Xu, S Han, S Ren, Y Wang… - IEEE Internet of …, 2023 - ieeexplore.ieee.org
The smart grid (SG) is a new type of grid that integrates traditional power grid with the
Internet of Things (IoT) to make the entire grid system more compatible, controllable, and self …

Breaking Secure Aggregation: Label Leakage from Aggregated Gradients in Federated Learning

Z Wang, Z Chang, J Hu, X Pang, J Du… - … -IEEE Conference on …, 2024 - ieeexplore.ieee.org
Federated Learning (FL) exhibits privacy vulnerabilities under gradient inversion attacks
(GIAs), which can extract private information from individual gradients. To enhance privacy …

Using Third-Party Auditor to Help Federated Learning: An Efficient Byzantine-robust Federated Learning

Z Zhang, L Wu, D He, J Li, N Lu… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Federated Learning (FL), as a distributed machine learning technique, has promise for
training models with distributed data in Artificial Intelligence of Things (AIoT). However, FL is …

A Socially Optimal Data Marketplace With Differentially Private Federated Learning

P Sun, G Liao, X Chen, J Huang - IEEE/ACM Transactions on …, 2024 - ieeexplore.ieee.org
Federated learning (FL) enables multiple data owners to collaboratively train machine
learning (ML) models for different model requesters while keeping data localized. Thus, FL …

IMPLEMENTATION OF CLASS INTERACTION UNDER AGGREGATION CONDITIONS.

O Kungurtsev, N Komleva - Eastern-European Journal of …, 2024 - search.ebscohost.com
The object of research is the implementation of relations between software classes. It is
shown that when implementing the aggregation relationship between classes, errors may …