Two-Phase Multi-Party Computation Enabled Privacy-Preserving Federated Learning

Countries across the globe have been pushing strict regulations on the protection of personal or private data collected. The traditional centralized machine learning method, where data is collected from end-users or IoT devices, so that it can discover insights behind real-world data, may not be fea...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Kanagavelu, Renuga, Li, Zengxiang, Samsudin, Juniarto, Yang, Yechao, Yang, Feng, Goh, Rick Siow Mong, Cheah, Mervyn, Wiwatphonthana, Praewpiraya, Akkarajitsakul, Khajonpong, Wangz, Shangguang
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Kanagavelu, Renuga
Li, Zengxiang
Samsudin, Juniarto
Yang, Yechao
Yang, Feng
Goh, Rick Siow Mong
Cheah, Mervyn
Wiwatphonthana, Praewpiraya
Akkarajitsakul, Khajonpong
Wangz, Shangguang
description Countries across the globe have been pushing strict regulations on the protection of personal or private data collected. The traditional centralized machine learning method, where data is collected from end-users or IoT devices, so that it can discover insights behind real-world data, may not be feasible for many data-driven industry applications in light of such regulations. A new machine learning method, coined by Google as Federated Learning (FL) enables multiple participants to train a machine learning model collectively without directly exchanging data. However, recent studies have shown that there is still a possibility to exploit the shared models to extract personal or confidential data. In this paper, we propose to adopt Multi Party Computation (MPC) to achieve privacy-preserving model aggregation for FL. The MPC-enabled model aggregation in a peer-to-peer manner incurs high communication overhead with low scalability. To address this problem, the authors proposed to develop a two-phase mechanism by 1) electing a small committee and 2) providing MPC-enabled model aggregation service to a larger number of participants through the committee. The MPC enabled FL framework has been integrated in an IoT platform for smart manufacturing. It enables a set of companies to train high quality models collectively by leveraging their complementary data-sets on their own premises, without compromising privacy, model accuracy vis-a-vis traditional machine learning methods and execution efficiency in terms of communication cost and execution time.
doi_str_mv 10.48550/arxiv.2005.11901
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2005_11901</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2005_11901</sourcerecordid><originalsourceid>FETCH-LOGICAL-a671-8de07d44e7e1335a9e4d2b6e064e721ee50cc87d2d595dede114962dc571cb033</originalsourceid><addsrcrecordid>eNotj0FOwzAURL3pArUcgFV9AQc7tuNkiaIWkIKaRfbRj_0BS2lSOW4gtycUViO9kWb0CHkQPFG51vwRwrefk5RznQhRcHFHTs3XyOpPmJC-XfvoWQ0hLrQcz5drhOjHgR4G6Hp0tA5-BruwOuCEYfbDBz2iwwBxLSuEMKxoRzbv0E94_59b0hwPTfnCqtPza_lUMciMYLlDbpxSaFBIqaFA5dIuQ56tKBWImlubG5c6XWi3ngihiix1VhthOy7lluz_Zm9G7SX4M4Sl_TVrb2byBwUPSW8</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Two-Phase Multi-Party Computation Enabled Privacy-Preserving Federated Learning</title><source>arXiv.org</source><creator>Kanagavelu, Renuga ; Li, Zengxiang ; Samsudin, Juniarto ; Yang, Yechao ; Yang, Feng ; Goh, Rick Siow Mong ; Cheah, Mervyn ; Wiwatphonthana, Praewpiraya ; Akkarajitsakul, Khajonpong ; Wangz, Shangguang</creator><creatorcontrib>Kanagavelu, Renuga ; Li, Zengxiang ; Samsudin, Juniarto ; Yang, Yechao ; Yang, Feng ; Goh, Rick Siow Mong ; Cheah, Mervyn ; Wiwatphonthana, Praewpiraya ; Akkarajitsakul, Khajonpong ; Wangz, Shangguang</creatorcontrib><description>Countries across the globe have been pushing strict regulations on the protection of personal or private data collected. The traditional centralized machine learning method, where data is collected from end-users or IoT devices, so that it can discover insights behind real-world data, may not be feasible for many data-driven industry applications in light of such regulations. A new machine learning method, coined by Google as Federated Learning (FL) enables multiple participants to train a machine learning model collectively without directly exchanging data. However, recent studies have shown that there is still a possibility to exploit the shared models to extract personal or confidential data. In this paper, we propose to adopt Multi Party Computation (MPC) to achieve privacy-preserving model aggregation for FL. The MPC-enabled model aggregation in a peer-to-peer manner incurs high communication overhead with low scalability. To address this problem, the authors proposed to develop a two-phase mechanism by 1) electing a small committee and 2) providing MPC-enabled model aggregation service to a larger number of participants through the committee. The MPC enabled FL framework has been integrated in an IoT platform for smart manufacturing. It enables a set of companies to train high quality models collectively by leveraging their complementary data-sets on their own premises, without compromising privacy, model accuracy vis-a-vis traditional machine learning methods and execution efficiency in terms of communication cost and execution time.</description><identifier>DOI: 10.48550/arxiv.2005.11901</identifier><language>eng</language><subject>Computer Science - Distributed, Parallel, and Cluster Computing</subject><creationdate>2020-05</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2005.11901$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2005.11901$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Kanagavelu, Renuga</creatorcontrib><creatorcontrib>Li, Zengxiang</creatorcontrib><creatorcontrib>Samsudin, Juniarto</creatorcontrib><creatorcontrib>Yang, Yechao</creatorcontrib><creatorcontrib>Yang, Feng</creatorcontrib><creatorcontrib>Goh, Rick Siow Mong</creatorcontrib><creatorcontrib>Cheah, Mervyn</creatorcontrib><creatorcontrib>Wiwatphonthana, Praewpiraya</creatorcontrib><creatorcontrib>Akkarajitsakul, Khajonpong</creatorcontrib><creatorcontrib>Wangz, Shangguang</creatorcontrib><title>Two-Phase Multi-Party Computation Enabled Privacy-Preserving Federated Learning</title><description>Countries across the globe have been pushing strict regulations on the protection of personal or private data collected. The traditional centralized machine learning method, where data is collected from end-users or IoT devices, so that it can discover insights behind real-world data, may not be feasible for many data-driven industry applications in light of such regulations. A new machine learning method, coined by Google as Federated Learning (FL) enables multiple participants to train a machine learning model collectively without directly exchanging data. However, recent studies have shown that there is still a possibility to exploit the shared models to extract personal or confidential data. In this paper, we propose to adopt Multi Party Computation (MPC) to achieve privacy-preserving model aggregation for FL. The MPC-enabled model aggregation in a peer-to-peer manner incurs high communication overhead with low scalability. To address this problem, the authors proposed to develop a two-phase mechanism by 1) electing a small committee and 2) providing MPC-enabled model aggregation service to a larger number of participants through the committee. The MPC enabled FL framework has been integrated in an IoT platform for smart manufacturing. It enables a set of companies to train high quality models collectively by leveraging their complementary data-sets on their own premises, without compromising privacy, model accuracy vis-a-vis traditional machine learning methods and execution efficiency in terms of communication cost and execution time.</description><subject>Computer Science - Distributed, Parallel, and Cluster Computing</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj0FOwzAURL3pArUcgFV9AQc7tuNkiaIWkIKaRfbRj_0BS2lSOW4gtycUViO9kWb0CHkQPFG51vwRwrefk5RznQhRcHFHTs3XyOpPmJC-XfvoWQ0hLrQcz5drhOjHgR4G6Hp0tA5-BruwOuCEYfbDBz2iwwBxLSuEMKxoRzbv0E94_59b0hwPTfnCqtPza_lUMciMYLlDbpxSaFBIqaFA5dIuQ56tKBWImlubG5c6XWi3ngihiix1VhthOy7lluz_Zm9G7SX4M4Sl_TVrb2byBwUPSW8</recordid><startdate>20200524</startdate><enddate>20200524</enddate><creator>Kanagavelu, Renuga</creator><creator>Li, Zengxiang</creator><creator>Samsudin, Juniarto</creator><creator>Yang, Yechao</creator><creator>Yang, Feng</creator><creator>Goh, Rick Siow Mong</creator><creator>Cheah, Mervyn</creator><creator>Wiwatphonthana, Praewpiraya</creator><creator>Akkarajitsakul, Khajonpong</creator><creator>Wangz, Shangguang</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20200524</creationdate><title>Two-Phase Multi-Party Computation Enabled Privacy-Preserving Federated Learning</title><author>Kanagavelu, Renuga ; Li, Zengxiang ; Samsudin, Juniarto ; Yang, Yechao ; Yang, Feng ; Goh, Rick Siow Mong ; Cheah, Mervyn ; Wiwatphonthana, Praewpiraya ; Akkarajitsakul, Khajonpong ; Wangz, Shangguang</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a671-8de07d44e7e1335a9e4d2b6e064e721ee50cc87d2d595dede114962dc571cb033</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Computer Science - Distributed, Parallel, and Cluster Computing</topic><toplevel>online_resources</toplevel><creatorcontrib>Kanagavelu, Renuga</creatorcontrib><creatorcontrib>Li, Zengxiang</creatorcontrib><creatorcontrib>Samsudin, Juniarto</creatorcontrib><creatorcontrib>Yang, Yechao</creatorcontrib><creatorcontrib>Yang, Feng</creatorcontrib><creatorcontrib>Goh, Rick Siow Mong</creatorcontrib><creatorcontrib>Cheah, Mervyn</creatorcontrib><creatorcontrib>Wiwatphonthana, Praewpiraya</creatorcontrib><creatorcontrib>Akkarajitsakul, Khajonpong</creatorcontrib><creatorcontrib>Wangz, Shangguang</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Kanagavelu, Renuga</au><au>Li, Zengxiang</au><au>Samsudin, Juniarto</au><au>Yang, Yechao</au><au>Yang, Feng</au><au>Goh, Rick Siow Mong</au><au>Cheah, Mervyn</au><au>Wiwatphonthana, Praewpiraya</au><au>Akkarajitsakul, Khajonpong</au><au>Wangz, Shangguang</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Two-Phase Multi-Party Computation Enabled Privacy-Preserving Federated Learning</atitle><date>2020-05-24</date><risdate>2020</risdate><abstract>Countries across the globe have been pushing strict regulations on the protection of personal or private data collected. The traditional centralized machine learning method, where data is collected from end-users or IoT devices, so that it can discover insights behind real-world data, may not be feasible for many data-driven industry applications in light of such regulations. A new machine learning method, coined by Google as Federated Learning (FL) enables multiple participants to train a machine learning model collectively without directly exchanging data. However, recent studies have shown that there is still a possibility to exploit the shared models to extract personal or confidential data. In this paper, we propose to adopt Multi Party Computation (MPC) to achieve privacy-preserving model aggregation for FL. The MPC-enabled model aggregation in a peer-to-peer manner incurs high communication overhead with low scalability. To address this problem, the authors proposed to develop a two-phase mechanism by 1) electing a small committee and 2) providing MPC-enabled model aggregation service to a larger number of participants through the committee. The MPC enabled FL framework has been integrated in an IoT platform for smart manufacturing. It enables a set of companies to train high quality models collectively by leveraging their complementary data-sets on their own premises, without compromising privacy, model accuracy vis-a-vis traditional machine learning methods and execution efficiency in terms of communication cost and execution time.</abstract><doi>10.48550/arxiv.2005.11901</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2005.11901
ispartof
issn
language eng
recordid cdi_arxiv_primary_2005_11901
source arXiv.org
subjects Computer Science - Distributed, Parallel, and Cluster Computing
title Two-Phase Multi-Party Computation Enabled Privacy-Preserving Federated Learning
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-02T01%3A55%3A04IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Two-Phase%20Multi-Party%20Computation%20Enabled%20Privacy-Preserving%20Federated%20Learning&rft.au=Kanagavelu,%20Renuga&rft.date=2020-05-24&rft_id=info:doi/10.48550/arxiv.2005.11901&rft_dat=%3Carxiv_GOX%3E2005_11901%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true