[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119827-en":3,"doc-seo-119827-105":30,"detail-sidebar-cat-0-en-105":95},{"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},119827,8796095360427,"Lucas Martin","https://ap-avatar.wpscdn.com/davatar_994ba38a5ba835b3df7d355c54d3ed8d",8,"Research & Report","Lattice-Based Cryptography for Privacy Preserving Machine Learning - Master’s Thesis in Computer Science","Digitization of healthcare data creates urgent privacy risks in healthcare machine learning. Federated Learning (FL) addresses this by training deep models collaboratively while sharing parameters rather than raw data. This thesis enhances a privacy-preserving federated learning approach for medical datasets using homomorphic encryption, extending prior work with multi-key homomorphic encryption. The study modifies an RLWE scheme, adapts a Python FL framework (Flower), and integrates encrypted communication using protocol buffers and updated training loops to secure model updates. Experiments confirm robust model performance via validation accuracy, precision, F1-score, and recall.","Faculty of Science and Technology  \nDepartment of Electrical Engineering and Computer Science  \nLattice-Based Cryptography for Privacy Preserving Machine Learning  \nMaster’s Thesis in Computer Science  \nby  \nIvar Walskaar and Minh Christian Tran  \nInternal Supervisors  \nSupervisor 1  \nSupervisor 2  \nExternal Supervisors  \nExternal Supervisor 1  \nExternal Supervisor 2  \nReviewers  \nReviewer1  \nReviewer2  \nJuly 12, 2023  \n’Everything is possible in your life when you believe. When you believe, everything is possible. You have two hands like me . Everything is possible. Go. Go. And take it, whatever you want to do’  \nYoel Romero  \nAbstract  \nThe digitization of healthcare data has presented a pressing need to address privacy concerns within the realm of machine learning for healthcare institutions. One promising solution is Federated Learning (FL), which enables collaborative training of deep machine learning models among medical institutions by sharing model parameters instead of raw data. This study focuses on enhancing an existing privacy-preserving federated learning algorithm for medical data through the utilization of homomorphic encryption, building upon prior research.  \nIn contrast to the previous paper this work is based upon by Wibawa, using a single key for homomorphic encryption, our proposed solution is a practical implementation of a preprint by Ma Jing [et. al. with a proposed](et. al. with a proposed) encryption scheme (xMK-CKKS) for implementing multi-key homomorphic encryption. For this, our work first involves modifying a simple “ring learning with error” RLWE scheme. We then fork a popular FL framework for python where we integrate our own communication process with protocol buffers before we locate and modify the library’s existing training loop in order to further enhance the security of model updates with the multi-key homomorphic encryption scheme. Our experimental evaluations validate that despite these modifications, our proposed framework maintains robust model performance, as demonstrated by consistent metrics including validation accuracy, precision, f1-score, and recall.  \nAcknowledgements  \nFirst we would like to extend our gratitude to Sander Låstad Olsen, a fellow student and friend, whose knowledge of Flower gave us a solid foundation to work on, and the tools he introduced us to significantly helped our debugging efforts in modifying Flower’s source code. Furthermore, we extend deep thanks to our supervising professor Ferhat Özgur Catak. His guidance during our weekly meetings helped shape our work and navigate us through challenging paths. We are deeply thankful for their invaluable contributions.  \nContents  \nAbstract iv  \nAcknowledgements v  \nList of Figures xi  \nList of Tables xiii  \nAbbreviations xv  \n1 Introduction 1  \n1. 1 Motivation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1  \n1.2 Problem Definition . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2  \n1.3 Objective . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2  \n1.4 Contributions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3  \n1.5 Outline . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3  \n2 Background 5  \n2. 1 Convolutional Neural Network . . . . . . . . . . . . . . . . . . . . . . . . 5  \n2.2 Privacy-preserving Federated learning . . . . . . . . . . . . . . . . . . . . 6  \n2.3 Flower: A Federated Learning Framework . . . . . . . . . . . . . . . . . . 7  \n2.4 Homomorphic Encryption . . . . . . . . . . . . . . . . . . . . . . . . . . . 8  \n2.5 Traditional vs. Lattice-Based Encryption . . . . . . . . . . . . . . . . . . 9  \n2.6 Multi-key Homomorphic encryption . . . . . . . . . . . . . . . . . . . . . 10  \n2.7 Protobuf and gRPC .............................. 10  \n2.8 Ring Learning With Errors (RLWE) ..................... 11  \n2.9 xMK-CKKS . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11  \n2.9.1 C","cbCaiqWYeCob2BqJ","https://ap.wps.com/l/cbCaiqWYeCob2BqJ","pdf",1908383,1,63,"English","en",105,"# Abstract\n# Acknowledgements\n# Contents\n## 1 Introduction\n## 2 Background\n## 3 Solution Approach\n## 4 Experimental Evaluation","[{\"question\":\"What problem does the thesis address in healthcare machine learning?\",\"answer\":\"It addresses privacy concerns when digitizing healthcare data and training machine learning models across institutions. The work focuses on privacy-preserving federated learning rather than sharing raw data.\"},{\"question\":\"How does the proposed approach improve federated learning privacy?\",\"answer\":\"It integrates homomorphic encryption into federated learning so that model updates can be secured. The thesis specifically builds toward multi-key homomorphic encryption.\"},{\"question\":\"What changes are made to frameworks or algorithms to support multi-key homomorphic encryption?\",\"answer\":\"The work modifies a ring learning with errors (RLWE) scheme and adapts the Flower federated learning framework. It incorporates a custom communication process using protocol buffers and updates the training loop to apply the multi-key encryption scheme.\"},{\"question\":\"How is the solution evaluated and what results are reported?\",\"answer\":\"The thesis performs experimental evaluations on model performance metrics. Results show robust validation accuracy along with precision, F1-score, and recall remaining consistent despite the integration changes.\"}]","Lattice-Based Cryptography for Privacy Preserving Machine Learning - Master’s Thesis in Computer Science | PDF",1785726515,159,{"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":90,"head_meta":92,"extra_data":94,"updated_unix":28},"lattice-based-cryptography-for-privacy-preserving-machine-learning-masters-thesis-in-computer-science","",{"@graph":36,"@context":89},[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/lattice-based-cryptography-for-privacy-preserving-machine-learning-masters-thesis-in-computer-science/119827/",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",[71,77,81,85],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the thesis address in healthcare machine learning?","Question",{"text":75,"@type":76},"It addresses privacy concerns when digitizing healthcare data and training machine learning models across institutions. The work focuses on privacy-preserving federated learning rather than sharing raw data.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the proposed approach improve federated learning privacy?",{"text":80,"@type":76},"It integrates homomorphic encryption into federated learning so that model updates can be secured. The thesis specifically builds toward multi-key homomorphic encryption.",{"name":82,"@type":73,"acceptedAnswer":83},"What changes are made to frameworks or algorithms to support multi-key homomorphic encryption?",{"text":84,"@type":76},"The work modifies a ring learning with errors (RLWE) scheme and adapts the Flower federated learning framework. It incorporates a custom communication process using protocol buffers and updates the training loop to apply the multi-key encryption scheme.",{"name":86,"@type":73,"acceptedAnswer":87},"How is the solution evaluated and what results are reported?",{"text":88,"@type":76},"The thesis performs experimental evaluations on model performance metrics. Results show robust validation accuracy along with precision, F1-score, and recall remaining consistent despite the integration changes.","https://schema.org",{"og:url":52,"og:type":91,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":93,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":96},[97,101,105,109,114,119,124,127,132,135,139],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":106,"show_sort_weight":107,"slug":108},"Exam",70,"exam",{"id":110,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},5,"Comic",60,"comic",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},6,"Technology",50,"technology",{"id":120,"doc_module":4,"doc_module_name":46,"category_name":121,"show_sort_weight":122,"slug":123},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":125,"slug":126},30,"research-report",{"id":128,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":130,"slug":131},9,"Religion & Spirituality",20,"religion-spirituality",{"id":130,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":130,"slug":134},"World Cup","world-cup",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":136,"slug":138},10,"Lifestyle","lifestyle",{"id":140,"doc_module":4,"doc_module_name":46,"category_name":141,"show_sort_weight":110,"slug":142},19,"General","general"]