Enhancing Differential Privacy for Federated Learning at Scale
Federated learning (FL) is an emerging technique that trains machine learning models across multiple de-centralized systems. It enables local devices to collaboratively learn a model by aggregating locally computed updates via a server. Privacy is a core aspect of FL, and recent works in this area a...
Saved in:
Main Authors: | Chunghun Baek, Sungwook Kim, Dongkyun Nam, Jihoon Park |
---|---|
Format: | article |
Language: | EN |
Published: |
IEEE
2021
|
Subjects: | |
Online Access: | https://doaj.org/article/ca4f5cebcb204fb6adf064ce48a9d83f |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
Federated Learning for Privacy-Preserving Speaker Recognition
by: Abraham Woubie, et al.
Published: (2021) -
Differential Privacy for IoT-Enabled Critical Infrastructure: A Comprehensive Survey
by: Muhammad Akbar Husnoo, et al.
Published: (2021) -
Sport Location-Based User Clustering With Privacy-Preservation in Wireless IoT-Driven Healthcare
by: Qiyun Zhang, et al.
Published: (2021) -
Review: Privacy-Preservation in the Context of Natural Language Processing
by: Darshini Mahendran, et al.
Published: (2021) -
<italic>p</italic>-Power Exponential Mechanisms for Differentially Private Machine Learning
by: Yanan Li, et al.
Published: (2021)