[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-123845-en":3,"doc-seo-123845-105":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},123845,4398048949847,"Eliana","https://ap-avatar.wpscdn.com/avatar/400002536579ef2da7f?_k=1778318612642679267",8,"Research & Report","Decentralized Machine Learning on Blockchain - Developing a Federated Learning based System - Thesis","Traditional machine learning often depends on a central server for training and aggregation, which introduces security risks, burdensome data storage, and high computational overhead. Federated Learning distributes model training to local devices and then aggregates updates centrally, improving customization and deployment flexibility while inheriting similar concerns around security and data handling. This thesis presents a decentralized approach that combines Federated Learning with Decentralized Machine Learning on an EVM-compatible blockchain to enhance transparency, trust, scalability, and efficiency through redesigned privacy mechanisms, decentralized smart contracts, and robustness against data poisoning attacks.","DECENTRALIZED MACHINE LEARNING ON BLOCKCHAIN: DEVELOPING A FEDERATED LEARNING BASED SYSTEM  \nA Thesis  \npresented to  \nthe Faculty of California Polytechnic State University,  \nSan Luis Obispo  \nIn Partial Fulfillment  \nof the Requirements for the Degree  \nMaster of Science in Computer Science  \nby  \nNikhil Sridhar  \nDecember 2023  \n© 2023  \nNikhil Sridhar ALL RIGHTS RESERVED  \nii  \nCOMMITTEE MEMBERSHIP  \nTITLE: Decentralized Machine Learning on  \nBlockchain: Developing a Federated Learning based System  \nAUTHOR: Nikhil Sridhar  \nDATE SUBMITTED: December 2023  \nCOMMITTEE CHAIR: Franz Kurfess, Ph.D.  \nProfessor of Computer Science  \nCOMMITTEE MEMBER: Maria Pantoja, Ph.D.  \nAssociate Professor of Computer Science  \nCOMMITTEE MEMBER: Zachary N J Peterson, Ph.D.  \nAssociate Professor of Computer Science  \nABSTRACT  \nDecentralized Machine Learning on Blockchain: Developing a Federated Learning  \nbased System  \nNikhil Sridhar  \nTraditional Machine Learning (ML) methods usually rely on a central server to perform ML tasks. However, these methods have problems like security risks, data storage issues, and high computational demands. Federated Learning (FL), on the other hand, spreads out the ML process. It trains models on local devices and then combines them centrally. While FL improves computing and customization, it still faces the same challenges as centralized ML in security and data storage.  \nThis thesis introduces a new approach combining Federated Learning and Decentralized Machine Learning (DML), which operates on an Ethereum Virtual Machine (EVM) compatible blockchain. The blockchain’s security and decentralized nature help improve transparency, trust, scalability, and efficiency. The main contributions of this thesis include:  \n1. Redesigning a semi-centralized system with enhanced privacy and the multiKRUM algorithm, following the work of Shayan et al..  \n2. Developing a new decentralized framework that supports both standard and deep-learning FL, using the InterPlanetary File System (IPFS) and Ethereum Virtual Machine (EVM)-compatible Smart Contracts.  \n3. Assessing how well the system defends against common data poisoning attacks, using a version of Multi-KRUM that’s better at detecting outliers.  \n4. Applying privacy methods to securely combine data from different sources.  \nACKNOWLEDGMENTS  \nThanks to:  \n• Andrew Guenther, for uploading this template.  \n• Prof. Kurfess for being understanding, patient, and guiding me in the right direction.  \n• Prof. Peterson and Prof. Pantoja for their patience and understanding.  \n• Prof. Kazerouni for guiding me through the Thesis Seminar class and pointing me in the right direction for the overall thesis.  \nTABLE OF CONTENTS  \nPage  \nLIST OF TABLES ................................. ix  \nLIST OF FIGURES ................................ x  \n1 INTRODUCTION ............................... 1  \n2 BACKGROUND ................................ 2  \n2.1 Decentralized Machine Learning ..................... 2  \n2.2 Federated Learning ............................ 2  \n2.2.1 Understanding Heterogeneity .................. 3  \n2.3 Federated Averaging Algorithms ..................... 4  \n2.3.1 FedAvg .............................. 4  \n2.3.2 q-FedAvg ............................. 5  \n2.3.3 Robust FedAvg with Multi-KRUM ............... 6  \n2.3.4 Robust q-FedAvg with Multi-KRUM .............. 6  \n2.3.5 FedProx .............................. 7  \n2.4 Blockchain ................................. 7  \n2.4.1 Ethereum Virtual Machine (EVM) ............... 7  \n2.4.2 Proof of Work (PoW) and Its Layers .............. 8  \n2.4.3 Brief Overview of Proof of Stake (PoS) ............. 8  \n2.4.4 Using Geth to Simulate a Private PoW Blockchain ...... 8  \n2.4.5 Decentralized File Storage and IPFS .............. 9  \n3 RELATED WORKS .............................. 10  \n3.1 Fully Decentralized Federated Learning ................. 10  \n3.2 VerifyNet: Secure Federated Learning .................. 11  \n3.3 Blockchained On-device ","cbCaiqjKNVVUk24H","https://ap.wps.com/l/cbCaiqjKNVVUk24H","pdf",1125311,1,59,"English","en",105,"# Table of Contents\n## Introduction\n## Background\n## Related Works\n## System Design\n## Testing and Validation","[{\"question\":\"为什么传统机器学习和中心化汇聚会带来问题？\",\"answer\":\"传统方法通常依赖中心服务器执行任务，容易产生安全风险、数据存储压力以及较高计算开销。\"},{\"question\":\"该论文如何将联邦学习与区块链结合来改进系统？\",\"answer\":\"论文提出在EVM兼容区块链上运行的联邦学习与去中心化机器学习结合方案，通过区块链的安全与去中心化特性提升透明度、信任、可扩展性和效率。\"},{\"question\":\"论文如何评估系统对数据投毒攻击的防御能力？\",\"answer\":\"通过使用改进版本的Multi-KRUM来检测离群值，并评估系统在常见数据投毒攻击下的防御效果。\"}]","Decentralized Machine Learning on Blockchain - Developing a Federated Learning based System - Thesis | PDF",1785818854,149,{"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},"decentralized-machine-learning-on-blockchain-developing-a-federated-learning-based-system-thesis","",{"@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/decentralized-machine-learning-on-blockchain-developing-a-federated-learning-based-system-thesis/123845/",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","2026-08-04",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},"为什么传统机器学习和中心化汇聚会带来问题？","Question",{"text":75,"@type":76},"传统方法通常依赖中心服务器执行任务，容易产生安全风险、数据存储压力以及较高计算开销。","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"该论文如何将联邦学习与区块链结合来改进系统？",{"text":80,"@type":76},"论文提出在EVM兼容区块链上运行的联邦学习与去中心化机器学习结合方案，通过区块链的安全与去中心化特性提升透明度、信任、可扩展性和效率。",{"name":82,"@type":73,"acceptedAnswer":83},"论文如何评估系统对数据投毒攻击的防御能力？",{"text":84,"@type":76},"通过使用改进版本的Multi-KRUM来检测离群值，并评估系统在常见数据投毒攻击下的防御效果。","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},[93,97,101,105,110,115,120,123,128,131,135],{"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":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]