Collusion Resistant Federated Learning with Oblivious Distributed Differential Privacy

Privacy-preserving federated learning enables a population of distributed clients to jointly learn a shared model while keeping client training data private, even from an untrusted server. Prior works do not provide efficient solutions that protect against collusion attacks in which parties collabor...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Byrd, David, Mugunthan, Vaikkunth, Polychroniadou, Antigoni, Balch, Tucker Hybinette
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 Byrd, David
Mugunthan, Vaikkunth
Polychroniadou, Antigoni
Balch, Tucker Hybinette
description Privacy-preserving federated learning enables a population of distributed clients to jointly learn a shared model while keeping client training data private, even from an untrusted server. Prior works do not provide efficient solutions that protect against collusion attacks in which parties collaborate to expose an honest client's model parameters. We present an efficient mechanism based on oblivious distributed differential privacy that is the first to protect against such client collusion, including the "Sybil" attack in which a server preferentially selects compromised devices or simulates fake devices. We leverage the novel privacy mechanism to construct a secure federated learning protocol and prove the security of that protocol. We conclude with empirical analysis of the protocol's execution speed, learning accuracy, and privacy performance on two data sets within a realistic simulation of 5,000 distributed network clients.
doi_str_mv 10.48550/arxiv.2202.09897
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2202_09897</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2202_09897</sourcerecordid><originalsourceid>FETCH-LOGICAL-a677-12253225d64eb09a6cb643a3a36fbb59cd2e965f8ca8062ca3e3bd8cbb5025393</originalsourceid><addsrcrecordid>eNotj8tOwzAQRb1hgQofwAr_QIJrJ469RCkFpEhFqOo2GtuTMlJIkPOA_j1pQVeju5gzIx3G7tYizUyeiweIPzSnUgqZCmtscc0OZd-200B9x99xoGGEbuRbDBhhxMArhNhRd-TfNH7wnWtppn4a-GYhI7npzGyoaTBiNxK0_C3SDP50w64aaAe8_e8V22-f9uVLUu2eX8vHKgFdFMlaylwtE3SGTljQ3ulMwRLdOJdbHyRanTfGgxFaelCoXDB-2Ynl0qoVu_97exGrvyJ9QjzVZ8H6Iqh-AfrmTN4</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Collusion Resistant Federated Learning with Oblivious Distributed Differential Privacy</title><source>arXiv.org</source><creator>Byrd, David ; Mugunthan, Vaikkunth ; Polychroniadou, Antigoni ; Balch, Tucker Hybinette</creator><creatorcontrib>Byrd, David ; Mugunthan, Vaikkunth ; Polychroniadou, Antigoni ; Balch, Tucker Hybinette</creatorcontrib><description>Privacy-preserving federated learning enables a population of distributed clients to jointly learn a shared model while keeping client training data private, even from an untrusted server. Prior works do not provide efficient solutions that protect against collusion attacks in which parties collaborate to expose an honest client's model parameters. We present an efficient mechanism based on oblivious distributed differential privacy that is the first to protect against such client collusion, including the "Sybil" attack in which a server preferentially selects compromised devices or simulates fake devices. We leverage the novel privacy mechanism to construct a secure federated learning protocol and prove the security of that protocol. We conclude with empirical analysis of the protocol's execution speed, learning accuracy, and privacy performance on two data sets within a realistic simulation of 5,000 distributed network clients.</description><identifier>DOI: 10.48550/arxiv.2202.09897</identifier><language>eng</language><subject>Computer Science - Artificial Intelligence ; Computer Science - Cryptography and Security ; Computer Science - Multiagent Systems</subject><creationdate>2022-02</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/2202.09897$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2202.09897$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Byrd, David</creatorcontrib><creatorcontrib>Mugunthan, Vaikkunth</creatorcontrib><creatorcontrib>Polychroniadou, Antigoni</creatorcontrib><creatorcontrib>Balch, Tucker Hybinette</creatorcontrib><title>Collusion Resistant Federated Learning with Oblivious Distributed Differential Privacy</title><description>Privacy-preserving federated learning enables a population of distributed clients to jointly learn a shared model while keeping client training data private, even from an untrusted server. Prior works do not provide efficient solutions that protect against collusion attacks in which parties collaborate to expose an honest client's model parameters. We present an efficient mechanism based on oblivious distributed differential privacy that is the first to protect against such client collusion, including the "Sybil" attack in which a server preferentially selects compromised devices or simulates fake devices. We leverage the novel privacy mechanism to construct a secure federated learning protocol and prove the security of that protocol. We conclude with empirical analysis of the protocol's execution speed, learning accuracy, and privacy performance on two data sets within a realistic simulation of 5,000 distributed network clients.</description><subject>Computer Science - Artificial Intelligence</subject><subject>Computer Science - Cryptography and Security</subject><subject>Computer Science - Multiagent Systems</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj8tOwzAQRb1hgQofwAr_QIJrJ469RCkFpEhFqOo2GtuTMlJIkPOA_j1pQVeju5gzIx3G7tYizUyeiweIPzSnUgqZCmtscc0OZd-200B9x99xoGGEbuRbDBhhxMArhNhRd-TfNH7wnWtppn4a-GYhI7npzGyoaTBiNxK0_C3SDP50w64aaAe8_e8V22-f9uVLUu2eX8vHKgFdFMlaylwtE3SGTljQ3ulMwRLdOJdbHyRanTfGgxFaelCoXDB-2Ynl0qoVu_97exGrvyJ9QjzVZ8H6Iqh-AfrmTN4</recordid><startdate>20220220</startdate><enddate>20220220</enddate><creator>Byrd, David</creator><creator>Mugunthan, Vaikkunth</creator><creator>Polychroniadou, Antigoni</creator><creator>Balch, Tucker Hybinette</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20220220</creationdate><title>Collusion Resistant Federated Learning with Oblivious Distributed Differential Privacy</title><author>Byrd, David ; Mugunthan, Vaikkunth ; Polychroniadou, Antigoni ; Balch, Tucker Hybinette</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a677-12253225d64eb09a6cb643a3a36fbb59cd2e965f8ca8062ca3e3bd8cbb5025393</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Computer Science - Artificial Intelligence</topic><topic>Computer Science - Cryptography and Security</topic><topic>Computer Science - Multiagent Systems</topic><toplevel>online_resources</toplevel><creatorcontrib>Byrd, David</creatorcontrib><creatorcontrib>Mugunthan, Vaikkunth</creatorcontrib><creatorcontrib>Polychroniadou, Antigoni</creatorcontrib><creatorcontrib>Balch, Tucker Hybinette</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Byrd, David</au><au>Mugunthan, Vaikkunth</au><au>Polychroniadou, Antigoni</au><au>Balch, Tucker Hybinette</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Collusion Resistant Federated Learning with Oblivious Distributed Differential Privacy</atitle><date>2022-02-20</date><risdate>2022</risdate><abstract>Privacy-preserving federated learning enables a population of distributed clients to jointly learn a shared model while keeping client training data private, even from an untrusted server. Prior works do not provide efficient solutions that protect against collusion attacks in which parties collaborate to expose an honest client's model parameters. We present an efficient mechanism based on oblivious distributed differential privacy that is the first to protect against such client collusion, including the "Sybil" attack in which a server preferentially selects compromised devices or simulates fake devices. We leverage the novel privacy mechanism to construct a secure federated learning protocol and prove the security of that protocol. We conclude with empirical analysis of the protocol's execution speed, learning accuracy, and privacy performance on two data sets within a realistic simulation of 5,000 distributed network clients.</abstract><doi>10.48550/arxiv.2202.09897</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2202.09897
ispartof
issn
language eng
recordid cdi_arxiv_primary_2202_09897
source arXiv.org
subjects Computer Science - Artificial Intelligence
Computer Science - Cryptography and Security
Computer Science - Multiagent Systems
title Collusion Resistant Federated Learning with Oblivious Distributed Differential Privacy
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T22%3A17%3A45IST&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=Collusion%20Resistant%20Federated%20Learning%20with%20Oblivious%20Distributed%20Differential%20Privacy&rft.au=Byrd,%20David&rft.date=2022-02-20&rft_id=info:doi/10.48550/arxiv.2202.09897&rft_dat=%3Carxiv_GOX%3E2202_09897%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