LoMar: Regional Defence Counter Poisoning Attack on Federated Learning
Keywords:
.Abstract
The training data stays spread to distant clients in a network using federated learning (FL), which offers a highly efficient decentralised machine learning solution. Even if FL makes it possible to use IoT devices to build a mobile edge computing framework that protects user privacy, new research shows that this can be vulnerable to poisoning assaults performed by distant clients.
Downloads
References
J. Konecnˇ y, H. B. McMahan, F. X. Yu, P. Richt ´ arik, A. T. Suresh, ´ and D. Bacon, “Federated improving 2017. learning: Strategies
communication for efficiency,”
B. McMahan, E. Moore, D. Ramage, S. Hampson, and B. A. y Arcas, “Communication-efficient learning of deep networks from decentralized data,” in Artificial Intelligence and Statistics, pp. 1273– 1282, 2017.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Attribution — You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
NonCommercial — You may not use the material for commercial purposes.
No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.
