[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-117852-en":3,"doc-seo-117852-105":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},117852,962075006959,"Anda","https://ap-avatar.wpscdn.com/avatar/e0002397efbe92a78e?_k=1776741047341049297",8,"Research & Report","Realizing Privacy-Preserving Machine Learning Through Hybrid Homomorphic Encryption","Rising adoption of machine learning (ML) for complex data analysis has increased the value of accurate models for scientists, businesses, and everyday users. Standard ML, however, can leak sensitive information, threatening confidentiality of private datasets. This thesis surveys privacy-preserving techniques such as differential privacy, homomorphic encryption, and secure multi-party computation, focusing on efficiency and usability limits. Two hybrid homomorphic encryption (HHE) protocols are proposed for machine-learning-as-a-service environments and evaluated against a strong adversary, showing improved computational and communication efficiency, reduced privacy leakage, and practicality for resource-limited devices.","Mindaugas Budzys  \nRealizing Privacy-Preserving Machine Learning Through Hybrid Homomorphic Encryption  \nFaculty of Information Technology and Communication Sciences (ITC) Master’s thesis  \nMarch 2023  \nAbstract  \nMindaugas Budzys: Realizing Privacy-Preserving Machine Learning Through Hybrid Homomorphic Encryption  \nMaster’s thesis Tampere University  \nMasters Degree Programme in Information Security March 2023  \nThe rising popularity of machine learning (ML) in modern day data analysis has allowed scientist, businesses and ordinary users to gain access to powerful tools, which provide accurate insight into complex data. However, as more research is done into ML, it has been noticed that standard ML models experience privacy leakage, which can jeopardize the confidentiality of sensitive data. Because of this reason, researchers began looking in to applying privacy-preserving techniques, such as differential privacy, homomorphic encryption or secure multi-party computation in ML to create privacy-preserving machine learning (PPML) . Adaptation of these novel techniques have been limited because of well documented limitations of the techniques, which affect the efficiency and the usability of the ML model. To help progress the field and help with adaptation, this thesis covers in detail the existing methods used in PPML and covers the limitations of state-of-the-art approaches. Additionally, two novel hybrid homomorphic encryption (HHE) protocols are proposed to show the practical viability of PPML in machine-learning-as-a-service environments. Experiments conducted on these protocols show high promise in terms of computational and communication efficiency, when compared to standard homomorphic encryption approaches. The provided efficiency paves the way towards applying HHE in resource-limited devices and make PPML available for a larger variety of devices. The protocols are analysed against a powerful adversary to show the security of the protocol and that the privacy leakage of the ML model is reduced.  \nKeywords: Hybrid Homomorphic Encryption, Machine Learning-as-a-Service, Privacypreserving Machine Learning  \nThe originality of this thesis has been checked using the Turnitin Originality Check service.  \nContents  \n1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1  \n2 Preliminaries . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4  \n2. 1 Machine Learning, Datasets and Attacks . . . . . . . . . . . . . . . . 4  \n2.2 Privacy-Preserving Techniques . . . . . . . . . . . . . . . . . . . . . . 8  \n2.2. 1 Differential Privacy . . . . . . . . . . . . . . . . . . . . . . . . . 8  \n2.2.2 Homomorphic Encryption . . . . . . . . . . . . . . . . . . . . . . 8  \n2.2.3 Secure Multi-party Computation . . . . . . . . . . . . . . . . . . 13  \n3 Privacy-Preserving Machine Learning approaches in Literature . . . . . . . 16  \n3.1 State-of-the-Art: Differential Privacy .................. 16  \n3.2 State-of-the-Art: Homomorphic Encryption .............. 17  \n3.3 State-of-the-Art: Secure Multi-party Computation ........... 19  \n4 Evaluation of State-of-the-Art . . . . . . . . . . . . . . . . . . . . . . . . . 21  \n4. 1 HE protocols . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 21  \n4.2 Analysis of HE . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 23  \n4.3 SMPC Protocols . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 26  \n4.4 Analysis of SMPC protocols . . . . . . . . . . . . . . . . . . . . . . . 27  \n5 Realizing PPML Through HHE . . . . . . . . . . . . . . . . . . . . . . . . 30  \n5. 1 System Model . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 30  \n5.2 Threat Model . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 30  \n5.3 Protocol Constructions . . . . . . . . . . . . . . . . . . . . . . . . . . 32  \n5.3. 1 Two-Party Approach . . . . . . . . . . . . . . . . . . . . . . . . . 32  \n5.3.2 Three-party approach . . . . . . . . . . . . . . . .","cbCaipb5hQ88h7Oi","https://ap.wps.com/l/cbCaipb5hQ88h7Oi","pdf",375192,1,60,"English","en",105,"# 1 Introduction\n# 2 Preliminaries\n## 2.1 Machine Learning, Datasets and Attacks\n## 2.2 Privacy-Preserving Techniques\n# 3 Privacy-Preserving Machine Learning approaches in Literature\n# 4 Evaluation of State-of-the-Art\n# 5 Realizing PPML Through HHE\n# 6 Experimental Results\n# 7 Conclusions & Future Directions\n# References","[{\"question\":\"Why does machine learning require privacy-preserving techniques?\",\"answer\":\"ML models may expose confidential information through attacks or privacy leakage related to model behavior, endangering sensitive data. Privacy regulations further increase the need to protect data used for training and inference.\"},{\"question\":\"What privacy-preserving methods are reviewed in this thesis?\",\"answer\":\"The thesis covers differential privacy, homomorphic encryption, and secure multi-party computation as foundational approaches for privacy-preserving machine learning (PPML). It also analyzes their limitations affecting efficiency and usability.\"},{\"question\":\"What is proposed, and what results are reported for the proposed protocols?\",\"answer\":\"Two hybrid homomorphic encryption (HHE) protocols are proposed for machine-learning-as-a-service environments. Experiments show high promise in computational and communication efficiency compared with standard homomorphic encryption, while security analysis against a powerful adversary reduces privacy leakage.\"}]","Realizing Privacy-Preserving Machine Learning Through Hybrid Homomorphic Encryption | PDF",1785680003,151,{"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},"realizing-privacy-preserving-machine-learning-through-hybrid-homomorphic-encryption","",{"@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/realizing-privacy-preserving-machine-learning-through-hybrid-homomorphic-encryption/117852/",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},"Why does machine learning require privacy-preserving techniques?","Question",{"text":75,"@type":76},"ML models may expose confidential information through attacks or privacy leakage related to model behavior, endangering sensitive data. Privacy regulations further increase the need to protect data used for training and inference.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What privacy-preserving methods are reviewed in this thesis?",{"text":80,"@type":76},"The thesis covers differential privacy, homomorphic encryption, and secure multi-party computation as foundational approaches for privacy-preserving machine learning (PPML). It also analyzes their limitations affecting efficiency and usability.",{"name":82,"@type":73,"acceptedAnswer":83},"What is proposed, and what results are reported for the proposed protocols?",{"text":84,"@type":76},"Two hybrid homomorphic encryption (HHE) protocols are proposed for machine-learning-as-a-service environments. Experiments show high promise in computational and communication efficiency compared with standard homomorphic encryption, while security analysis against a powerful adversary reduces privacy leakage.","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},[93,97,101,105,109,114,119,122,127,130,134],{"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":21,"slug":108},5,"Comic","comic",{"id":110,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},7,"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"]