[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118196-en":3,"doc-seo-118196-105":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":4,"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},118196,8796095461564,"Liam","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","DECML - Distributed Edge Consensus Machine Learning Framework","Rising dependence on interdependent data-driven services in IoT, smart homes, and Industry 4.0 is constrained by siloed security and privacy controls. Prior approaches such as federated learning and distributed machine learning, including differential privacy and homomorphic encryption, still struggle with guaranteeing robust privacy and security. DECML introduces a distributed edge consensus framework that supports secure, privacy-preserving insight sharing among stakeholders without revealing underlying data or models. Queries are distributed and responses aggregated via independent nodes, matching local accuracy with low added latency, as shown in a 20-node evaluation.","DECML: Distributed Edge Consensus Machine  \nLearning Framework  \nCyrile Verdeyen􀀃 , Carlton Shepherdy , Konstantinos Markantonakisz , Raja Naeem Akramx , Roger Milroy{ ,  \nSarah Abu Ghazalahk , and Damien Sauveron􀀃􀀃  \n􀀃 Awin, Amsterdam, The Netherlands, Email: Cyrile.verdeyen@gmail.com  \ny Newcastle University, Newcastle upon Tyne, United Kingdom, Email: [carlton.shepherd@newcastle.ac.uk](carlton.shepherd@newcastle.ac.uk)  \nz Royal Holloway, University of London, Egham, United Kingdom, [Email: K.Markantonakis@rhul.ac.uk](Email: K.Markantonakis@rhul.ac.uk)  \nx University of Aberdeen, Aberdeen, United Kingdom, Email: [raja.akram@abdn.ac.uk](raja.akram@abdn.ac.uk)  \n{ Independent researcher, Email: [roger@milroy.dev](roger@milroy.dev)[ ](roger@milroy.dev)k King Khalid University, Abha, Saudi Arabia, Email: [sabugazalah@kku.edu.sa](sabugazalah@kku.edu.sa)[ ](sabugazalah@kku.edu.sa)􀀃􀀃 University of Limoges, Limoges, France, Email: damien.sauveron@unilim.fr  \nAbstract—The increasing reliance on interdependent datadriven services in the Internet of Things (IoT), smart homes, and Industry 4.0 is hindered by siloed security and privacy measures. Existing solutions like federated learning and distributed machine learning, with their various approaches such as differential privacy and homomorphic encryption, while promising, face challenges in ensuring robust security and privacy. We introduce Distributed Edge Consensus Machine Learning (DECML), a novel framework that enables secure, privacypreserving insights sharing among multiple stakeholders without exposing underlying data or models. DECML distributes queries and aggregates responses through independent nodes, achieving accuracy comparable to local deployments with minimal added latency. Our evaluation, using standard datasets and a 20-node network, demonstrates DECML's potential for collaborative decision-making without compromising privacy. This has significant implications for domains such as cybersecurity, healthcare, and financial services, where privacy concerns hinder data sharing.  \nIndex Terms—Machine Learning, Edge Computing, Distributed Computing, Data Privacy  \nI. INTRODUCTION  \nFor organisations, cybersecurity challenges are increasing in complexity when it comes to data sharing, especially inan age of machine learning (ML) and deep learning (DL) where jointly developed models can yield significant benefits. In particular, DL architectures can effectively classify and generate patterns without the need for highly parametric models or expert-led feature engineering. This property makes them very useful in application domains awash with raw data; for example, malware classification [1], [2], program vulnerability detection [3], [4], anti-money laundering (AML) systems [5],[6], and medical imaging [7],[8] where data sharing may yield enormous benefits.  \nData sharing in areas like cybersecurity and healthcare can significantly benefit from collaborative machine learning. However, traditional methods, including federated learning (FML), raise concerns about privacy and security. While FML allows for collaborative model training without direct data sharing, it remains vulnerable to inference attacks where malicious actors can deduce sensitive information about the  \ntraining data from shared model updates or parameters [9],[10], [11] . Furthermore, attacks like model inversion can compromise the privacy of individual data points.  \nDistributed Edge Consensus Machine Learning (DECML) addresses these concerns by enabling organizations to share insights without exposing raw data or model parameters. Unlike FML, DECML focuses on sharing the outcomes of local models (i.e., insights) rather than model parameters or updates. This is achieved through a decentralized architecture where:  \n1) Each node trains its own ML model on its private data.  \n2) Nodes join the DECML network and specify query preferences.  \n3) An orchestrator distributes queries and aggregates responses.  \n4) Nodes vote ","cbCaijlwgOR0odCZ","https://ap.wps.com/l/cbCaijlwgOR0odCZ","pdf",292725,1,7,"English","en",105,"# Abstract\n# Introduction\n# Related Works","[{\"question\":\"What problem does DECML target in data sharing for IoT and Industry 4.0?\",\"answer\":\"DECML targets the limitations created by siloed security and privacy measures that hinder collaborative, data-driven services. It focuses on enabling insight sharing without exposing sensitive data or models.\"},{\"question\":\"How does DECML differ from federated learning in privacy preservation?\",\"answer\":\"DECML shares the outcomes of local models (insights) rather than model parameters or updates. It uses decentralized query distribution, response aggregation, and node voting to reach consensus.\"},{\"question\":\"What architecture steps are used in the DECML workflow?\",\"answer\":\"Each node trains an ML model on private data, joins the DECML network and sets query preferences, an orchestrator distributes queries and aggregates responses, and nodes vote on responses to form a consensus.\"}]","DECML - Distributed Edge Consensus Machine Learning Framework | PDF",1785682119,18,{"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},"decml-distributed-edge-consensus-machine-learning-framework","",{"@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/decml-distributed-edge-consensus-machine-learning-framework/118196/",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","2026-08-02",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does DECML target in data sharing for IoT and Industry 4.0?","Question",{"text":75,"@type":76},"DECML targets the limitations created by siloed security and privacy measures that hinder collaborative, data-driven services. It focuses on enabling insight sharing without exposing sensitive data or models.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does DECML differ from federated learning in privacy preservation?",{"text":80,"@type":76},"DECML shares the outcomes of local models (insights) rather than model parameters or updates. It uses decentralized query distribution, response aggregation, and node voting to reach consensus.",{"name":82,"@type":73,"acceptedAnswer":83},"What architecture steps are used in the DECML workflow?",{"text":84,"@type":76},"Each node trains an ML model on private data, joins the DECML network and sets query preferences, an orchestrator distributes queries and aggregates responses, and nodes vote on responses to form a consensus.","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},[93,97,101,105,110,115,119,122,127,130,134],{"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":21,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]