[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-125461-en":3,"doc-seo-125461-105":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},125461,1099514068365,"Aurelia","https://ap-avatar.wpscdn.com/avatar/10000253d8d9f28188e?_k=1776742907772140068",8,"Research & Report","Farcaster sybil account detection using graph-based and machine learning models - Final report","Farcaster, a blockchain-based social network with over 800,000 registered accounts, is vulnerable to Sybil attacks where fraudulent users create multiple fake accounts to capture financial incentives and spread malicious content. This thesis proposes a hybrid detection approach that combines SybilSCAR graph-based signals with an ensemble of LightGBM, Random Forest, and XGBoost using text, behavioral, and network-structure features. Evaluation on ~4,000 Sybil samples and 400 verified human accounts shows improved performance, with ROC AUC reaching 0.99, supporting mixed-methods effectiveness for practical client-side filtering.","FEDERAL UNIVERSITY OF SANTA CATARINA  \nTECHNOLOGY CENTER  \nAUTOMATION AND SYSTEMS ENGINEERING DEPARTMENT UNDERGRADUATE COURSE IN CONTROL AND AUTOMATION ENGINEERING  \nJean Guilherme Neiverth  \nFarcaster sybil account detection using graph-based and machine learning  \nmodels  \nFlorianópolis  \nJean Guilherme Neiverth  \nFarcaster sybil account detection using graph-based and machine learning  \nmodels  \nFinal report of the subject DAS5511 (Course Final Project) as a Concluding Dissertation of the Undergraduate Course in Control and Automation Engineering of the Federal University of Santa Catarina. Supervisor: Prof. Leandro Buss Becker, Dr.  \nCo-supervisor: José Fernando Rosa Ribeiro  \nFlorianópolis  \nFicha catalográfica gerada por meio de sistema automatizado gerenciado pela BU/UFSC.  \nDados inseridos pelo próprio autor.  \nNeiverth, Jean Guilherme  \nFarcaster sybil account detection using graph-based and machine learning models / Jean Guilherme Neiverth ; orientador, Leandro Buss Becker, coorientador, José Fernando Rosa Ribeiro, 2025.  \n66 p .  \nTrabalho de Conclusão de Curso (graduação) -Universidade Federal de Santa Catarina, Centro Tecnológico, Graduação em Engenharia de Controle e Automação, Florianópolis, 2025.  \nInclui referências .  \n1. Engenharia de Controle e Automação . 2. Sybil Attack detection . 3. Graph-based algorithm . 4. Machine learning model . I . Becker, Leandro Buss . II . Ribeiro, José Fernando Rosa . III . Universidade Federal de Santa Catarina .  \nGraduação em Engenharia de Controle e Automação . IV . Título .  \nJean Guilherme Neiverth  \nFarcaster sybil account detection using graph-based and machine learning  \nmodels  \nThis dissertation was evaluated in the context of the subject DAS5511 (Course Final Project) and approved in its final form by the Undergraduate Course in Control and  \nAutomation Engineering  \nFlorianópolis, August 04-th, 2025 .  \nProf. Marcelo de Lellis Costa de Oliveira, Dr.  \nCourse Coordinator  \nExamining Board:  \nProf. Leandro Buss Becker, Dr.  \nAdvisor  \nUFSC/CTC/DAS  \nJosé Fernando Rosa Ribeiro Supervisor  \nBleu Studio  \nProf. Públio Macedo Monteiro Lima, Dr. Evaluator  \nUFSC/CTC/DAS  \nProf. Hector Bressa Silveira, Dr.  \nBoard President UFSC/CTC/DAS  \nACKNOWLEDGEMENTS  \nI am deeply grateful to my parents, whose commitment to my education and unconditional support throughout my undergraduate journey made this achievement possible. To my brother, my companion during these years, thank you for standing by me through every challenge. I would also like to thank my girlfriend Emmanuele, who brought support into my life during this project’s completion.  \nMy professional growth owes much to José Ribeiro, whose mentorship opened doors to work alongside the exceptional Bleu team. I’m equally grateful to my colleagues there, who invested in both my personal development and the success of this project with remarkable generosity.  \nI Would also like to thank the Professors at DAS, for the educational excellence, elevating standards not only at UFSC but throughout Brazil. Special recognition goes tomy advisor, Leandro Becker, whose guidance and constructive feedback proved crucial throughout this process.  \nTo NEO Empresarial, that provided valuable connections and transformative experiences that shaped my professional identity in ways I continue to appreciate.  \nFinally, to my fellow students, especially Juliano Nunes, Juan Amorim, Luis Parise, Leonardo Clivati, and Ian Marchetti, thank you for your companionship through demanding semesters and for generously sharing your knowledge along the way.  \nDISCLAIMER  \nFlorianópolis, August 04-th, 2025 .  \nAs representative of the Bleu Studio company in which the present work was carried out, I declare this document to be exempt from any confidential or sensitive content regarding intellectual property, that may keep it from being published by the Federal University of Santa Catarina (UFSC) to the general public, including its online availability in the In","cbCaid6Iw0cT7M0x","https://ap.wps.com/l/cbCaid6Iw0cT7M0x","pdf",2312760,1,67,"English","en",105,"# Introduction\n## Problem: Sybil attacks on Farcaster\n## Proposed hybrid detection approach\n# Methodology\n## Graph-based component (SybilSCAR)\n## Machine learning ensemble models\n## Feature engineering (text, behavior, network structure)\n# Evaluation\n## Dataset composition (Sybil vs verified human accounts)\n## Performance comparison using ROC AUC\n# Results and Discussion\n## Why hybrid approaches outperform single methods\n## Practical implications for Farcaster clients","[{\"question\":\"What problem does the thesis address on Farcaster?\",\"answer\":\"The thesis addresses Sybil attacks on Farcaster, where attackers create multiple fake accounts to exploit incentives and distribute malicious content.\"},{\"question\":\"What is the hybrid detection approach proposed?\",\"answer\":\"It combines a graph-based component (SybilSCAR) with a machine learning ensemble of LightGBM, Random Forest, and XGBoost using text, behavioral, and network-structure features.\"},{\"question\":\"How well does the hybrid method perform compared with single methods?\",\"answer\":\"On the evaluated dataset, the hybrid approach achieves ROC AUC of 0.99, outperforming 0.95 for the standalone graph-based algorithm and 0.98 for the machine learning model alone.\"}]","Farcaster sybil account detection using graph-based and machine learning models - Final report | PDF",1785899130,169,{"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},"farcaster-sybil-account-detection-using-graph-based-and-machine-learning-models-final-report","",{"@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/farcaster-sybil-account-detection-using-graph-based-and-machine-learning-models-final-report/125461/",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","2026-08-05",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 the thesis address on Farcaster?","Question",{"text":75,"@type":76},"The thesis addresses Sybil attacks on Farcaster, where attackers create multiple fake accounts to exploit incentives and distribute malicious content.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What is the hybrid detection approach proposed?",{"text":80,"@type":76},"It combines a graph-based component (SybilSCAR) with a machine learning ensemble of LightGBM, Random Forest, and XGBoost using text, behavioral, and network-structure features.",{"name":82,"@type":73,"acceptedAnswer":83},"How well does the hybrid method perform compared with single methods?",{"text":84,"@type":76},"On the evaluated dataset, the hybrid approach achieves ROC AUC of 0.99, outperforming 0.95 for the standalone graph-based algorithm and 0.98 for the machine learning model alone.","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"]