[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-117129-en":3,"doc-seo-117129-105":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},117129,549758252649,"Ivy","https://ap-avatar.wpscdn.com/avatar/8000253669c5317157?_k=1778319167496531819",8,"Research & Report","Secure Multi-Party Computation for Machine Learning - A Survey","Machine learning enables extracting insights from data originating from diverse sources, but real deployments increasingly rely on data contributed by multiple entities. Protecting contributors’ privacy is therefore essential to maintain integrity and fairness in collaborative learning. This survey reviews recent advances in secure multi-party computation (SMPC) for machine learning, assessing security models, requirements, system types, and service models aligned with IEEE practices. It classifies SMPC approaches into homomorphic encryption and secret-sharing based systems, then identifies gaps such as security requirements, streamlined information exchange, incentives, data authenticity, and operational efficiency, motivating more holistic protocol design.","This article has been accepted for publication in IEEE Access. This is the author's version which has not been fully edited and content may change prior to final publication. Citation information: DOI 10. 1109/ACCESS.2024.3388992  \nDate of publication xxxx 00, 0000, date of current version xxxx 00, 0000 .  \nDigital Object Identifier 10.1109/ACCESS.2017.DOI  \nSecure Multi-Party Computation for Machine Learning: A Survey  \nIAN ZHOU1 ,(Member, IEEE,), FARZAD TOFIGH1 ,(Member, IEEE), MASSIMO PICCARDI1 ,(Senior Member, IEEE), MEHRAN ABOLHASAN1 ,(Senior Member, IEEE), DANIEL FRANKLIN1 ,(Member, IEEE) and JUSTIN LIPMAN1 ,(Senior Member, IEEE)  \n1 School of Electrical and Data Engineering, University of Technology Sydney, Sydney, NSW 2007 Australia Corresponding author: Farzad Tofigh (e-mail: farzad.tofigh@ uts.edu.au) .  \nThe authors acknowledge the support of Food Agility CRC Ltd, funded under the Commonwealth Government CRC Program. The financial and in-kind support of Robert Bosch (Australia) Pty Ltd & Robert Bosch GmbH in completing this work is also acknowledged.  \n ABSTRACT Machine learning is a powerful technology for extracting information from data of diverse nature and origin. As its deployment increasingly depends on data from multiple entities, ensuring privacy for these contributors becomes paramount for the integrity and fairness of machine learning endeavors. This review looks into the recent advancements in secure multi-party computation (SMPC) for machine learning, a pivotal technology championing data privacy. We evaluate these applications from various aspects, including security models, requirements, system types, and service models, aligning with the IEEE’s recommended practices for SMPC. Broadly, SMPC systems are divided into two categories: homomorphicbased systems, which facilitate computations on encrypted data, ensuring data remains confidential, and secret sharing-based systems, which disseminate data across parties in fragmented shares. Our literature analysis highlights certain gaps, such as security requisites, streamlined information exchange, incentive structures, data authenticity, and operational efficiency. Recognizing these challenges lead to envisioning a holistic SMPC protocol tailored for machine learning applications.  \n INDEX TERMS Multi-party computation, Machine learning, Federated learning, Data privacy, Cryptography, Protocols  \nI. INTRODUCTION  \nIN an ever-advancing world increasingly saturated with  \ndata, recent technological developments such as the Internet of Things (IoT) [1], wireless sensor networks, cloud computing, and machine learning provide different means and methods to extract and process these data. Moreover, sensitive information can be derived from the analysis of data. Data and data analysis applications, collectively referred to as machine learning, have significantly impacted many different fields and industries [2]–[4] . The processing of data could involve multiple parties from different backgrounds for collaborative purposes. Organizations and individuals might want their data, method or model to remain private during collaborative operations. A recent 2022 report [5] from IBM has revealed limited data security in many organisations. 83% of these organisations had more than one data breach at an average cost of USD 4.35 million - increasing by 12.7% since 2020 . The increasing cost reflects the importance of data security [6] .  \nSecure Multi-Party Computation (SMPC) has gathered significant interest as a technological solution to data privacy and security concerns. SMPC represents a privacy-preserving approach that allows multiple parties to jointly compute the function of (y1 , y2 ,..., yi) ← f (x1 , x2 ,..., xi), where each party Pi provides input xi and computes yi. Leveraging the power of cryptography, SMPC enables these parties to collectively determine a result from their individual input data without disclosing any of this data to the other participants. Thu","cbCaioOSG8LQjzrZ","https://ap.wps.com/l/cbCaioOSG8LQjzrZ","pdf",777912,1,20,"English","en",105,"# Introduction\n## Secure Multi-Party Computation (SMPC) fundamentals\n## Motivation and privacy requirements\n## Related survey work and limitations","[{\"question\":\"Why is privacy protection critical in machine learning involving multiple data entities?\",\"answer\":\"Collaborative machine learning can expose sensitive information derived from data analysis. As deployments increasingly depend on data from multiple contributors, protecting privacy becomes essential for integrity and fairness.\"},{\"question\":\"What does secure multi-party computation (SMPC) enable in machine learning?\",\"answer\":\"SMPC allows multiple parties to compute a joint result from their individual inputs while keeping each party’s data confidential and undisclosed to other participants, using cryptography to coordinate computation.\"},{\"question\":\"How does the survey categorize SMPC approaches for machine learning?\",\"answer\":\"It divides SMPC systems into homomorphic encryption based systems, which compute directly on encrypted data, and secret sharing based systems, which distribute data as fragmented shares across parties.\"}]","Secure Multi-Party Computation for Machine Learning - A Survey | PDF",1785674031,50,{"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},"secure-multi-party-computation-for-machine-learning-a-survey","",{"@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/secure-multi-party-computation-for-machine-learning-a-survey/117129/",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 is privacy protection critical in machine learning involving multiple data entities?","Question",{"text":75,"@type":76},"Collaborative machine learning can expose sensitive information derived from data analysis. As deployments increasingly depend on data from multiple contributors, protecting privacy becomes essential for integrity and fairness.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What does secure multi-party computation (SMPC) enable in machine learning?",{"text":80,"@type":76},"SMPC allows multiple parties to compute a joint result from their individual inputs while keeping each party’s data confidential and undisclosed to other participants, using cryptography to coordinate computation.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the survey categorize SMPC approaches for machine learning?",{"text":84,"@type":76},"It divides SMPC systems into homomorphic encryption based systems, which compute directly on encrypted data, and secret sharing based systems, which distribute data as fragmented shares across parties.","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},[93,97,101,105,110,114,119,122,126,129,133],{"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":29,"slug":113},6,"Technology","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":21,"slug":125},9,"Religion & Spirituality","religion-spirituality",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":127,"show_sort_weight":21,"slug":128},"World Cup","world-cup",{"id":130,"doc_module":4,"doc_module_name":46,"category_name":131,"show_sort_weight":130,"slug":132},10,"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":46,"category_name":135,"show_sort_weight":106,"slug":136},19,"General","general"]