[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-125940-en":3,"doc-seo-125940-105":31,"detail-sidebar-cat-0-en-105":93},{"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":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},125940,137451207643,"Noah","https://ap-avatar.wpscdn.com/davatar_3d24733baf745e90a7e4bdd5f77d97b2",8,"Research & Report","Blind Evaluation Framework for Fully Homomorphic Encryption and Privacy-Preserving Machine Learning","Privacy-preserving machine learning often relies on fully homomorphic encryption (FHE) to enable secure data outsourcing to untrusted servers. While FHE supports arithmetic over encrypted data, it remains difficult to incorporate control structures such as decision statements that are essential for many ML models. Prior work frequently uses interactive rounds of decryption and evaluation (IRDE), which decrypt encrypted data periodically to process plaintext control logic. This thesis addresses the gap in non-interactive training for encrypted decision-tree models by introducing the Blind Evaluation Framework (BEF), enabling encrypted execution of control structures without evaluating conditional expressions.","Southern Methodist University  \nSMU Scholar  \n\n| Computer Science and Engineering Theses and Dissertations | Computer Science and Engineering |\n| --- | --- |\n| Spring 5-11-2024\u003Cbr>Blind Evaluation Framework for Fully Homomorphic Encryption and Privacy-Preserving Machine Learning\u003Cbr>Hunjae Lee\u003Cbr>Southern Methodist University, [hunjael@smu.edu](hunjael@smu.edu)\u003Cbr>Follow this and additional works at: [https://scholar.smu.edu/engineering_compsci_etds](https://scholar.smu.edu/engineering_compsci_etds) |  |\n\nRecommended Citation  \nLee, Hunjae, \"Blind Evaluation Framework for Fully Homomorphic Encryption and Privacy-Preserving Machine Learning\" (2024) . Computer Science and Engineering Theses and Dissertations. 38.  \n[https://scholar.smu.edu/engineering_compsci_etds/38](https://scholar.smu.edu/engineering_compsci_etds/38)  \nThis Thesis is brought to you for free and open access by the Computer Science and Engineering at SMU Scholar. It has been accepted for inclusion in Computer Science and Engineering Theses and Dissertations by an authorized administrator of SMU Scholar. For more information, please visit [http://digitalrepository.smu.edu](http://digitalrepository.smu.edu).  \nBLIND EVALUATION FRAMEWORK FOR FULLY HOMOMORPHIC ENCRYPTION  \nAND  \nPRIVACY-PRESERVING MACHINE LEARNING  \nApproved by:  \n\n| Dr. Corey Clark\u003Cbr>Assistant Professor |\n| --- |\n| Dr. Eric Larson\u003Cbr>Associate Professor |\n\nDr. King Ip Lin Associate Professor  \nBLIND EVALUATION FRAMEWORK FOR FULLY HOMOMORPHIC ENCRYPTION  \nAND  \nPRIVACY-PRESERVING MACHINE LEARNING  \nA Dissertation Presented to the Graduate Faculty of the Lyle School of Engineering  \nSouthern Methodist University  \nin  \nPartial Fulfillment of the Requirements  \nfor the degree of  \nMaster of Science  \nwith a  \nMajor in Computer Science  \nby  \nHunjae Lee  \nB.S., Computer Science, Southern Methodist University  \nMay 11, 2024  \nCopyright (2024)  \nHunjae Lee  \nAll Rights Reserved  \nAcknowledgments  \nThis work was funded by BALANCED Media|Technology (BMT), a company that may potentially benefit from the research results. Dr. Corey Clark has an equity interest in BMT and also serves as the company’s chief technology officer. The terms of this arrangement have been reviewed and approved by Southern Methodist University in accordance with its conflict of interest policies.  \nLee, Hunjae B.S. , Computer Science, Southern Methodist University  \nBlind Evaluation Framework for Fully Homomorphic Encryption  and   \nPrivacy-Preserving Machine Learning  \nAdvisor: Dr. Corey Clark  \nMaster of Science degree conferred May 11, 2024 Dissertation completed April 12, 2024  \nVarious approaches to privacy-preserving machine learning (PPML) using Fully Homomorphic Encryption (FHE) have been developed, focusing on secure data outsourcing to untrusted servers by data owners. While FHE enables arithmetic operations on encrypted data, it struggles with integrating control structures like decision statements essential for machine learning models. Because of this, FHE is used primarily for arithmetic tasks. Nonarithmetic programming logic, such as control structures, are handled outside the encrypted domain using Interactive Rounds of Decryption and Evaluation (IRDE), where encrypted data is periodically decrypted for plaintext processing, highlighting the challenge of direct evaluation on encrypted data.  \nWhile non-interactive inference protocols have been demonstrated in prior works owing to their relative logical simplicity, development of non-interactive training protocols have gone largely unaddressed. In decision tree training for example, the current state-of-the-art requires d-rounds of IRDE for tree-depth of d. To address this issue in PPML and FHE, we introduce the Blind Evaluation Framework (BEF), a cryptographically secure programming framework that enables execution of control structures and logical statements in encrypted space without evaluating the necessary conditional expressions. BEF facilitates encrypted functio","cbCaiug1YNiHsszk","https://ap.wps.com/l/cbCaiug1YNiHsszk","pdf",608620,10,1,52,"English","en",105,"# List of Figures\n# List of Tables\n# Chapter 1 Introduction\n## Fully Homomorphic Encryption\n## FHE over the Boolean\n## Boolean Circuits for logical and arithmetic operations\n## Terminology\n## Existing Methods that Address Limitations of FHE\n# Chapter 2 Related Work\n## Privacy-Preserving Machine Learning\n## Privacy-Preserving Decision Trees\n## Multi-Party Computation Approaches\n## Client-Server Models","[{\"question\":\"Why do interactive rounds of decryption and evaluation (IRDE) appear in FHE-based privacy-preserving machine learning?\",\"answer\":\"FHE handles arithmetic on encrypted data, but control structures like decision statements are difficult to evaluate directly in the encrypted domain. IRDE decrypts data periodically so plaintext logic can be applied.\"},{\"question\":\"What problem does the Blind Evaluation Framework (BEF) target?\",\"answer\":\"BEF targets the largely unaddressed development of non-interactive training protocols for PPML under FHE, including the high IRDE round requirements in decision tree training.\"},{\"question\":\"How does BEF enable training and inference without IRDE?\",\"answer\":\"BEF provides cryptographically secure control-structure execution in encrypted space while avoiding evaluation of the necessary conditional expressions, enabling encrypted functions such as branching and argmin/argmax.\"}]","Blind Evaluation Framework for Fully Homomorphic Encryption and Privacy-Preserving Machine Learning | PDF",1785902143,131,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":88,"head_meta":90,"extra_data":92,"updated_unix":29},"blind-evaluation-framework-for-fully-homomorphic-encryption-and-privacy-preserving-machine-learning-125940","",{"@graph":37,"@context":87},[38,55,70],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,49,52],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":48},"https://docshare.wps.com/document/","Document",2,{"item":50,"name":12,"@type":44,"position":51},"https://docshare.wps.com/document/research-report/",3,{"item":53,"name":13,"@type":44,"position":54},"https://docshare.wps.com/document/blind-evaluation-framework-for-fully-homomorphic-encryption-and-privacy-preserving-machine-learning-125940/125940/",4,{"url":53,"name":13,"@type":56,"author":57,"headline":13,"publisher":59,"fileFormat":62,"inLanguage":24,"description":14,"dateModified":63,"datePublished":64,"encodingFormat":62,"isAccessibleForFree":65,"interactionStatistic":66},"DigitalDocument",{"name":9,"@type":58},"Person",{"url":42,"name":60,"@type":61},"DocShare","Organization","application/pdf","2026-08-25","2026-08-05",true,{"@type":67,"interactionType":68,"userInteractionCount":20},"InteractionCounter",{"@type":69},"ViewAction",{"@type":71,"mainEntity":72},"FAQPage",[73,79,83],{"name":74,"@type":75,"acceptedAnswer":76},"Why do interactive rounds of decryption and evaluation (IRDE) appear in FHE-based privacy-preserving machine learning?","Question",{"text":77,"@type":78},"FHE handles arithmetic on encrypted data, but control structures like decision statements are difficult to evaluate directly in the encrypted domain. IRDE decrypts data periodically so plaintext logic can be applied.","Answer",{"name":80,"@type":75,"acceptedAnswer":81},"What problem does the Blind Evaluation Framework (BEF) target?",{"text":82,"@type":78},"BEF targets the largely unaddressed development of non-interactive training protocols for PPML under FHE, including the high IRDE round requirements in decision tree training.",{"name":84,"@type":75,"acceptedAnswer":85},"How does BEF enable training and inference without IRDE?",{"text":86,"@type":78},"BEF provides cryptographically secure control-structure execution in encrypted space while avoiding evaluation of the necessary conditional expressions, enabling encrypted functions such as branching and argmin/argmax.","https://schema.org",{"og:url":53,"og:type":89,"og:title":13,"og:site_name":60,"og:description":14},"article",{"robots":91,"canonical":53},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":94},[95,99,103,107,112,117,122,125,130,133,136],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":96,"show_sort_weight":97,"slug":98},"Story & Novel",90,"story-novel",{"id":48,"doc_module":4,"doc_module_name":47,"category_name":100,"show_sort_weight":101,"slug":102},"Literature",80,"literature",{"id":54,"doc_module":4,"doc_module_name":47,"category_name":104,"show_sort_weight":105,"slug":106},"Exam",70,"exam",{"id":108,"doc_module":4,"doc_module_name":47,"category_name":109,"show_sort_weight":110,"slug":111},5,"Comic",60,"comic",{"id":113,"doc_module":4,"doc_module_name":47,"category_name":114,"show_sort_weight":115,"slug":116},6,"Technology",50,"technology",{"id":118,"doc_module":4,"doc_module_name":47,"category_name":119,"show_sort_weight":120,"slug":121},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":123,"slug":124},30,"research-report",{"id":126,"doc_module":4,"doc_module_name":47,"category_name":127,"show_sort_weight":128,"slug":129},9,"Religion & Spirituality",20,"religion-spirituality",{"id":128,"doc_module":4,"doc_module_name":47,"category_name":131,"show_sort_weight":128,"slug":132},"World Cup","world-cup",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":134,"show_sort_weight":20,"slug":135},"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":47,"category_name":138,"show_sort_weight":108,"slug":139},19,"General","general"]