[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121050-en":3,"doc-seo-121050-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},121050,2336464648322,"Aria","https://ap-avatar.wpscdn.com/avatar/2200025388227c56fec?_k=1778556882303663488",8,"Research & Report","Detecting and Mitigating Data Integrity Attacks on Distributed Algorithms for Optimal Power Flow using Machine Learning","Distributed algorithms coordinate multiple agents to jointly solve optimal power flow problems, but adversaries can exploit the data exchanged among agents to tamper with algorithm behavior. This paper introduces a machine learning approach to detect and mitigate data integrity attacks affecting distributed OPF algorithms. In an offline phase with trustworthy data, agents train and share models of local subproblems. During online execution, each agent uses neighboring agents’ models with a reputation system to identify attacks and reduce their impact, yielding near-feasible and near-optimal operating points.","Proceedings of the 57th Hawaii International Conference on System Sciences | 2024  \nDetecting and Mitigating Data Integrity Attacks on Distributed Algorithms for Optimal Power Flow using Machine Learning  \nRachel Harris and Daniel K. Molzahn  \nGeorgia Institute of Technology  \n{rharris94, [molzahn](molzahn}@gatech.edu)[}](molzahn}@gatech.edu)[@gatech.edu](molzahn}@gatech.edu)  \nAbstract  \nUsing distributed algorithms, multiple computing agents can coordinate their operations by jointly solving optimal power flow problems. However, cyberattacks on the data communicated among agents may maliciously alter the behavior of a distributed algorithm. To improve cybersecurity, this paper proposes a machine learning method for detecting and mitigating data integrity attacks on distributed algorithms for solving optimal power flow problems. In an offline stage with trustworthy data, agents train and share machine learning models of their local subproblems. During online execution, each agent uses the trained models from neighboring agents to detect cyberattacks using a reputation system and then mitigate their impacts. Numerical results show that this method reliably, accurately, and quickly detects data integrity attacks and effectively mitigates their impacts to achieve near-feasible and near-optimal operating points.  \nKeywords: Cybersecurity, Distributed Optimization, Optimal Power Flow, Data Integrity Attack  \n1. Introduction  \nRapid deployments of distributed energy resources (DERs) motivate the development of new algorithms to optimize performance while respecting network limits. Traditional optimization relying on a central operator may not be practical for complex networks with widespread DER integration. Distributed optimization provides an alternative whereby multiple computing agents iteratively solve optimization problems by communicating the values of boundary variables. By enabling parallel computations, these algorithms have potential advantages in scalability [1] . However, since these algorithms rely on repeated communications between agents, they are vulnerable to data integrity attacks. An adversary who takes control of an agent or  \nSupport from NSF AI Institute for Advances in Optimization (AI4OPT), \\#2112533 .  \nattacks communication links could disrupt the system or manipulate the system’s operating point to profit financially. This paper proposes a machine learning method for detecting and mitigating cyberattacks on distributed optimal power flow (OPF) algorithms.  \nWe focus on the popular alternating direction method of multipliers (ADMM) algorithm, but our method can also be applied to other distributed algorithms such as auxiliary problem principle (APP) [2] or analytical target cascading (ATC) [3] . In these algorithms, local computing agents solve OPF subproblems for their region of the network that are augmented with constraints which ensure power flow consistency with neighboring agents. These algorithms alternate between solving augmented local subproblems and sharing boundary variable values to update the consistency constraints. When this shared data is corrupted, convergence is impaired [4],[5] .  \nEarly work on distributed OPF cyberattack vulnerability includes [6], [7], which develops an attack strategy for distributed primal-dual gradient descent DC OPF algorithms. This work is extended to AC OPF problems in [8] . The adversary determinesa target solution, which is sub-optimal overall but profitable to the attacker, and shares false data which corresponds to that target solution. Building on this work, our prior research in [9], [10] explores two additional cyberattacks on DC OPF problems and develops a machine learning detection method. The first attack strategy uses PID feedback control principles to gradually approach the target solution, while the second uses bilevel optimization to maximize profit.  \nSome prior work aims to detect and mitigate the impacts of these attacks. The method in [6]–[8]","cbCaio6vBAC8QiCF","https://ap.wps.com/l/cbCaio6vBAC8QiCF","pdf",603676,1,10,"English","en",105,"# Abstract\n# 1. Introduction\n## Distributed optimization and OPF with communication boundary variables\n## Vulnerability to data integrity attacks\n## Prior work on distributed OPF cyberattacks and defenses\n## Proposed machine learning-based detection and mitigation approach","[{\"question\":\"What problem does the paper address in distributed optimal power flow algorithms?\",\"answer\":\"It addresses cyberattacks that maliciously alter data integrity in communications among agents, impairing distributed algorithm behavior while solving optimal power flow problems.\"},{\"question\":\"How does the proposed method detect attacks during online execution?\",\"answer\":\"Agents use machine learning models shared in an offline phase and a reputation system that leverages neighboring agents’ predicted future behavior to detect data integrity attacks.\"},{\"question\":\"What mitigation result does the method achieve after detection?\",\"answer\":\"Numerical results indicate it effectively mitigates attack impacts, producing near-feasible and near-optimal operating points while detecting attacks reliably, accurately, and quickly.\"}]","Detecting and Mitigating Data Integrity Attacks on Distributed Algorithms for Optimal Power Flow using Machine Learning | PDF",1785733492,25,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"detecting-and-mitigating-data-integrity-attacks-on-distributed-algorithms-for-optimal-power-flow-using-machine-learning","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/detecting-and-mitigating-data-integrity-attacks-on-distributed-algorithms-for-optimal-power-flow-using-machine-learning/121050/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the paper address in distributed optimal power flow algorithms?","Question",{"text":75,"@type":76},"It addresses cyberattacks that maliciously alter data integrity in communications among agents, impairing distributed algorithm behavior while solving optimal power flow problems.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the proposed method detect attacks during online execution?",{"text":80,"@type":76},"Agents use machine learning models shared in an offline phase and a reputation system that leverages neighboring agents’ predicted future behavior to detect data integrity attacks.",{"name":82,"@type":73,"acceptedAnswer":83},"What mitigation result does the method achieve after detection?",{"text":84,"@type":76},"Numerical results indicate it effectively mitigates attack impacts, producing near-feasible and near-optimal operating points while detecting attacks reliably, accurately, and quickly.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,134],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":21,"slug":133},"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]