From distributed machine learning to federated learning: In the view of data privacy and security
Summary Federated learning is an improved version of distributed machine learning that further offloads operations which would usually be performed by a central server. The server becomes more like an assistant coordinating clients to work together rather than micromanaging the workforce as in tradi...
Published in: | Concurrency and Computation: Practice and Experience |
---|---|
Main Authors: | , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Wiley
2020
|
Subjects: | |
Online Access: | http://dx.doi.org/10.1002/cpe.6002 https://onlinelibrary.wiley.com/doi/pdf/10.1002/cpe.6002 https://onlinelibrary.wiley.com/doi/full-xml/10.1002/cpe.6002 |
id |
crwiley:10.1002/cpe.6002 |
---|---|
record_format |
openpolar |
spelling |
crwiley:10.1002/cpe.6002 2024-06-23T07:52:23+00:00 From distributed machine learning to federated learning: In the view of data privacy and security Shen, Sheng Zhu, Tianqing Wu, Di Wang, Wei Zhou, Wanlei 2020 http://dx.doi.org/10.1002/cpe.6002 https://onlinelibrary.wiley.com/doi/pdf/10.1002/cpe.6002 https://onlinelibrary.wiley.com/doi/full-xml/10.1002/cpe.6002 en eng Wiley http://onlinelibrary.wiley.com/termsAndConditions#vor Concurrency and Computation: Practice and Experience volume 34, issue 16 ISSN 1532-0626 1532-0634 journal-article 2020 crwiley https://doi.org/10.1002/cpe.6002 2024-06-13T04:22:12Z Summary Federated learning is an improved version of distributed machine learning that further offloads operations which would usually be performed by a central server. The server becomes more like an assistant coordinating clients to work together rather than micromanaging the workforce as in traditional DML. One of the greatest advantages of federated learning is the additional privacy and security guarantees it affords. Federated learning architecture relies on smart devices, such as smartphones and IoT sensors, that collect and process their own data, so sensitive information never has to leave the client device. Rather, clients train a submodel locally and send an encrypted update to the central server for aggregation into the global model. These strong privacy guarantees make federated learning an attractive choice in a world where data breaches and information theft are common and serious threats. This survey outlines the landscape and latest developments in data privacy and security for federated learning. We identify the different mechanisms used to provide privacy and security, such as differential privacy, secure multiparty computation and secure aggregation. We also survey the current attack models, identifying the areas of vulnerability and the strategies adversaries use to penetrate federated systems. The survey concludes with a discussion on the open challenges and potential directions of future work in this increasingly popular learning paradigm. Article in Journal/Newspaper DML Wiley Online Library Concurrency and Computation: Practice and Experience 34 16 |
institution |
Open Polar |
collection |
Wiley Online Library |
op_collection_id |
crwiley |
language |
English |
description |
Summary Federated learning is an improved version of distributed machine learning that further offloads operations which would usually be performed by a central server. The server becomes more like an assistant coordinating clients to work together rather than micromanaging the workforce as in traditional DML. One of the greatest advantages of federated learning is the additional privacy and security guarantees it affords. Federated learning architecture relies on smart devices, such as smartphones and IoT sensors, that collect and process their own data, so sensitive information never has to leave the client device. Rather, clients train a submodel locally and send an encrypted update to the central server for aggregation into the global model. These strong privacy guarantees make federated learning an attractive choice in a world where data breaches and information theft are common and serious threats. This survey outlines the landscape and latest developments in data privacy and security for federated learning. We identify the different mechanisms used to provide privacy and security, such as differential privacy, secure multiparty computation and secure aggregation. We also survey the current attack models, identifying the areas of vulnerability and the strategies adversaries use to penetrate federated systems. The survey concludes with a discussion on the open challenges and potential directions of future work in this increasingly popular learning paradigm. |
format |
Article in Journal/Newspaper |
author |
Shen, Sheng Zhu, Tianqing Wu, Di Wang, Wei Zhou, Wanlei |
spellingShingle |
Shen, Sheng Zhu, Tianqing Wu, Di Wang, Wei Zhou, Wanlei From distributed machine learning to federated learning: In the view of data privacy and security |
author_facet |
Shen, Sheng Zhu, Tianqing Wu, Di Wang, Wei Zhou, Wanlei |
author_sort |
Shen, Sheng |
title |
From distributed machine learning to federated learning: In the view of data privacy and security |
title_short |
From distributed machine learning to federated learning: In the view of data privacy and security |
title_full |
From distributed machine learning to federated learning: In the view of data privacy and security |
title_fullStr |
From distributed machine learning to federated learning: In the view of data privacy and security |
title_full_unstemmed |
From distributed machine learning to federated learning: In the view of data privacy and security |
title_sort |
from distributed machine learning to federated learning: in the view of data privacy and security |
publisher |
Wiley |
publishDate |
2020 |
url |
http://dx.doi.org/10.1002/cpe.6002 https://onlinelibrary.wiley.com/doi/pdf/10.1002/cpe.6002 https://onlinelibrary.wiley.com/doi/full-xml/10.1002/cpe.6002 |
genre |
DML |
genre_facet |
DML |
op_source |
Concurrency and Computation: Practice and Experience volume 34, issue 16 ISSN 1532-0626 1532-0634 |
op_rights |
http://onlinelibrary.wiley.com/termsAndConditions#vor |
op_doi |
https://doi.org/10.1002/cpe.6002 |
container_title |
Concurrency and Computation: Practice and Experience |
container_volume |
34 |
container_issue |
16 |
_version_ |
1802643675190132736 |