Detecting Shared Data Manipulation in Distributed Optimization Algorithms

This paper investigates the vulnerability of the Alternating Direction Method of Multipliers (ADMM) algorithm to shared data manipulation, with a focus on solving optimal power flow (OPF) problems. Deliberate data manipulation may cause the ADMM algorithm to converge to suboptimal solutions. We deri...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2023-10
Hauptverfasser: Alkhraijah, Mohannad, Harris, Rachel, Litchfield, Samuel, Huggins, David, Molzahn, Daniel K
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Alkhraijah, Mohannad
Harris, Rachel
Litchfield, Samuel
Huggins, David
Molzahn, Daniel K
description This paper investigates the vulnerability of the Alternating Direction Method of Multipliers (ADMM) algorithm to shared data manipulation, with a focus on solving optimal power flow (OPF) problems. Deliberate data manipulation may cause the ADMM algorithm to converge to suboptimal solutions. We derive two sufficient conditions for detecting data manipulation based on the theoretical convergence trajectory of the ADMM algorithm. We evaluate the detection conditions' performance on three data manipulation strategies we previously proposed: simple, feedback, and bilevel optimization attacks. We then extend these three data manipulation strategies to avoid detection by considering both the detection conditions and a neural network (NN) detection model in the attacks. We also propose an adversarial NN training framework to detect shared data manipulation. We illustrate the performance of our data manipulation strategy and detection framework on OPF problems. The results show that the proposed detection conditions successfully detect most of the data manipulation attacks. However, a bilevel optimization attack strategy that incorporates the detection methods may avoid being detected. Countering this, our proposed adversarial training framework detects all the instances of the bilevel optimization attack.
format Article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2880584832</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2880584832</sourcerecordid><originalsourceid>FETCH-proquest_journals_28805848323</originalsourceid><addsrcrecordid>eNqNyrEKwjAUQNEgCBbtPwScC_Gl1axiFR3EQfcSNbavtElNXha_XkE_wOkO545YAlIuMpUDTFgaQiuEgOUKikIm7FAaMjdCW_Nzo72581KT5kdtcYidJnSWo-UlBvJ4jfQZTgNhj6-vrbvaeaSmDzM2fugumPTXKZvvtpfNPhu8e0YTqGpd9PZDFSglCpUrCfK_6w2s0zzi</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2880584832</pqid></control><display><type>article</type><title>Detecting Shared Data Manipulation in Distributed Optimization Algorithms</title><source>Free E- Journals</source><creator>Alkhraijah, Mohannad ; Harris, Rachel ; Litchfield, Samuel ; Huggins, David ; Molzahn, Daniel K</creator><creatorcontrib>Alkhraijah, Mohannad ; Harris, Rachel ; Litchfield, Samuel ; Huggins, David ; Molzahn, Daniel K</creatorcontrib><description>This paper investigates the vulnerability of the Alternating Direction Method of Multipliers (ADMM) algorithm to shared data manipulation, with a focus on solving optimal power flow (OPF) problems. Deliberate data manipulation may cause the ADMM algorithm to converge to suboptimal solutions. We derive two sufficient conditions for detecting data manipulation based on the theoretical convergence trajectory of the ADMM algorithm. We evaluate the detection conditions' performance on three data manipulation strategies we previously proposed: simple, feedback, and bilevel optimization attacks. We then extend these three data manipulation strategies to avoid detection by considering both the detection conditions and a neural network (NN) detection model in the attacks. We also propose an adversarial NN training framework to detect shared data manipulation. We illustrate the performance of our data manipulation strategy and detection framework on OPF problems. The results show that the proposed detection conditions successfully detect most of the data manipulation attacks. However, a bilevel optimization attack strategy that incorporates the detection methods may avoid being detected. Countering this, our proposed adversarial training framework detects all the instances of the bilevel optimization attack.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Algorithms ; Convergence ; Neural networks ; Optimization ; Power flow ; Training</subject><ispartof>arXiv.org, 2023-10</ispartof><rights>2023. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</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>776,780</link.rule.ids></links><search><creatorcontrib>Alkhraijah, Mohannad</creatorcontrib><creatorcontrib>Harris, Rachel</creatorcontrib><creatorcontrib>Litchfield, Samuel</creatorcontrib><creatorcontrib>Huggins, David</creatorcontrib><creatorcontrib>Molzahn, Daniel K</creatorcontrib><title>Detecting Shared Data Manipulation in Distributed Optimization Algorithms</title><title>arXiv.org</title><description>This paper investigates the vulnerability of the Alternating Direction Method of Multipliers (ADMM) algorithm to shared data manipulation, with a focus on solving optimal power flow (OPF) problems. Deliberate data manipulation may cause the ADMM algorithm to converge to suboptimal solutions. We derive two sufficient conditions for detecting data manipulation based on the theoretical convergence trajectory of the ADMM algorithm. We evaluate the detection conditions' performance on three data manipulation strategies we previously proposed: simple, feedback, and bilevel optimization attacks. We then extend these three data manipulation strategies to avoid detection by considering both the detection conditions and a neural network (NN) detection model in the attacks. We also propose an adversarial NN training framework to detect shared data manipulation. We illustrate the performance of our data manipulation strategy and detection framework on OPF problems. The results show that the proposed detection conditions successfully detect most of the data manipulation attacks. However, a bilevel optimization attack strategy that incorporates the detection methods may avoid being detected. Countering this, our proposed adversarial training framework detects all the instances of the bilevel optimization attack.</description><subject>Algorithms</subject><subject>Convergence</subject><subject>Neural networks</subject><subject>Optimization</subject><subject>Power flow</subject><subject>Training</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>BENPR</sourceid><recordid>eNqNyrEKwjAUQNEgCBbtPwScC_Gl1axiFR3EQfcSNbavtElNXha_XkE_wOkO545YAlIuMpUDTFgaQiuEgOUKikIm7FAaMjdCW_Nzo72581KT5kdtcYidJnSWo-UlBvJ4jfQZTgNhj6-vrbvaeaSmDzM2fugumPTXKZvvtpfNPhu8e0YTqGpd9PZDFSglCpUrCfK_6w2s0zzi</recordid><startdate>20231020</startdate><enddate>20231020</enddate><creator>Alkhraijah, Mohannad</creator><creator>Harris, Rachel</creator><creator>Litchfield, Samuel</creator><creator>Huggins, David</creator><creator>Molzahn, Daniel K</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20231020</creationdate><title>Detecting Shared Data Manipulation in Distributed Optimization Algorithms</title><author>Alkhraijah, Mohannad ; Harris, Rachel ; Litchfield, Samuel ; Huggins, David ; Molzahn, Daniel K</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_28805848323</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Algorithms</topic><topic>Convergence</topic><topic>Neural networks</topic><topic>Optimization</topic><topic>Power flow</topic><topic>Training</topic><toplevel>online_resources</toplevel><creatorcontrib>Alkhraijah, Mohannad</creatorcontrib><creatorcontrib>Harris, Rachel</creatorcontrib><creatorcontrib>Litchfield, Samuel</creatorcontrib><creatorcontrib>Huggins, David</creatorcontrib><creatorcontrib>Molzahn, Daniel K</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Alkhraijah, Mohannad</au><au>Harris, Rachel</au><au>Litchfield, Samuel</au><au>Huggins, David</au><au>Molzahn, Daniel K</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Detecting Shared Data Manipulation in Distributed Optimization Algorithms</atitle><jtitle>arXiv.org</jtitle><date>2023-10-20</date><risdate>2023</risdate><eissn>2331-8422</eissn><abstract>This paper investigates the vulnerability of the Alternating Direction Method of Multipliers (ADMM) algorithm to shared data manipulation, with a focus on solving optimal power flow (OPF) problems. Deliberate data manipulation may cause the ADMM algorithm to converge to suboptimal solutions. We derive two sufficient conditions for detecting data manipulation based on the theoretical convergence trajectory of the ADMM algorithm. We evaluate the detection conditions' performance on three data manipulation strategies we previously proposed: simple, feedback, and bilevel optimization attacks. We then extend these three data manipulation strategies to avoid detection by considering both the detection conditions and a neural network (NN) detection model in the attacks. We also propose an adversarial NN training framework to detect shared data manipulation. We illustrate the performance of our data manipulation strategy and detection framework on OPF problems. The results show that the proposed detection conditions successfully detect most of the data manipulation attacks. However, a bilevel optimization attack strategy that incorporates the detection methods may avoid being detected. Countering this, our proposed adversarial training framework detects all the instances of the bilevel optimization attack.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2023-10
issn 2331-8422
language eng
recordid cdi_proquest_journals_2880584832
source Free E- Journals
subjects Algorithms
Convergence
Neural networks
Optimization
Power flow
Training
title Detecting Shared Data Manipulation in Distributed Optimization Algorithms
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-02T10%3A07%3A45IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=Detecting%20Shared%20Data%20Manipulation%20in%20Distributed%20Optimization%20Algorithms&rft.jtitle=arXiv.org&rft.au=Alkhraijah,%20Mohannad&rft.date=2023-10-20&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2880584832%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2880584832&rft_id=info:pmid/&rfr_iscdi=true