[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-82331-en":3,"doc-seo-82331-105":29,"detail-sidebar-cat-0-en-105":90},{"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":13,"seo_description":14,"update_tm":27,"read_time":28},82331,1374391974585,"Genevieve","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Federated Learning Architecture Data Privacy and System Security Approaches","The study integrates homomorphic encryption with differential privacy to strengthen data privacy and system security in federated learning (FL). FL keeps data on local devices and avoids centralized collection, yet sensitive information can still leak through model updates. Homomorphic encryption enables computation on encrypted data, while differential privacy reduces the risk of extracting individual-level information from model outputs. Experiments on the Framingham, Pima Indians Diabetes, and Bank Marketing datasets show improved privacy with minimal accuracy loss, while client data heterogeneity is analyzed to guide parameter and training choices.","FEDERATED LEARNING ARCHITECTURE: DATA PRIVACY AND SYSTEM SECURITY APPROACHES  \nCagdas Karatas  \nDepartment of Computer Engineering Istanbul, Turkiye [cagdasfats@gmail.com](cagdasfats@gmail.com)  \nHibanur Karadogan  \nDepartment of Computer Engineering Istanbul, Turkiye[hkaradogan4455@gmail.com](hkaradogan4455@gmail.com)  \nAhmet Yasin Ertug  \nDepartment of Computer Engineering Istanbul, Turkiye [ahmetyasinertug@gmail.com](ahmetyasinertug@gmail.com)  \nBusra Buyuktanir  \nDepartment of Computer Engineering Istanbul, Turkiye  \n[busra.buyuktanir@marmara.edu.tr](busra.buyuktanir@marmara.edu.tr)  \narXiv :2607 .0939 1v 1 [ cs .CR] 10 Jul 2026  \nKazim Yildiz  \nDepartment of Computer Engineering Istanbul, Turkiye [kazim.yildiz@marmara.edu.tr](kazim.yildiz@marmara.edu.tr)  \nGozde Karatas Baydogmus  \nLoyola University Chicago, USA Biruni University, Turkiye [gkaratasbaydogmus@luc.edu](gkaratasbaydogmus@luc.edu)  \nABSTRACT  \nThis study explores the integration of homomorphic encryption and differential privacy techniques to enhance data privacy and security in Federated Learning (FL) systems. FL allows data to remain on local devices, eliminating the need for centralized data collection; however, sensitive information may still be leaked during model updates. To address this issue, homomorphic encryption enables computations on encrypted data, while differential privacy prevents the extraction of individual information through statistical techniques applied to model outputs. The proposed architecture was tested on the Framingham, Pima Indians Diabetes, and Bank Marketing datasets, revealing that enhanced privacy can be achieved without significantly compromising model accuracy. Furthermore, the impact of data heterogeneity among clients on model performance was analyzed, and it was concluded that strategies such as the careful selection of differential privacy parameters and training settings, along with the use of larger datasets, can improve the efficiency of FL. The findings demonstrate that privacy-preserving and high-performance artificial intelligence systems can be securely applied in sensitive domains such as healthcare and finance.  \nKeywords Federated Learning · Homomorphic Encryption · Data Privacy · Differential Privacy · Secure Machine Learning  \n1 Introduction  \nToday, artificial intelligence and machine learning are rapidly advancing with the development of models that require large amounts of data. However, concerns about data privacy and security lead to questioning centralized data collection methods [1] . In this context, federated learning is an innovative approach that enables model training by processing data locally on devices without collecting it on a central server [2] . This method, first introduced by Google in 2016 [3], offers significant advantages in both protecting individual users’ privacy and training effective artificial intelligence models on large datasets.  \nFederated learning (FL) [4] reduces privacy risks by ensuring that data remains on local devices; however, it presents some challenges in terms of security and privacy. Parameters transmitted during model updates can be analyzed by malicious actors, leading to the leakage of sensitive information. In particular, model inference and data reconstruction  \nFederated Learning Architecture: Data Privacy and System Security Approaches  \nattacks can cause local data to be exposed. Additionally, the security of the central server used in FL processes is of critical importance; attacks on the server can compromise the security of the entire system. Therefore, it is necessary to integrate additional security measures such as homomorphic encryption and secure multi-party computation in FL applications [5] .  \nHomomorphic encryption [6, 7] allows storing data in an encrypted form while simultaneously enabling mathematical operations to be performed on this data. In other words, even if data is encrypted, certain mathematical operations can be performed directly ","cbCaiqcAzLmZNsi6","https://ap.wps.com/l/cbCaiqcAzLmZNsi6","pdf",2380582,1,21,"English","en",105,"# Introduction\n# Homomorphic Encryption in Federated Learning\n## Encryption, Operation, and Decryption\n# Privacy-Preserving FL Architecture","[{\"question\":\"How does the proposed approach enhance privacy in federated learning?\",\"answer\":\"It combines homomorphic encryption to compute on encrypted data and differential privacy to prevent individual information extraction from model outputs.\"},{\"question\":\"Why are model updates a privacy and security concern in federated learning?\",\"answer\":\"Because transmitted parameters can be analyzed by malicious actors, enabling model inference and data reconstruction attacks that may expose local sensitive information.\"},{\"question\":\"What datasets were used to evaluate the architecture and what was the overall outcome?\",\"answer\":\"The architecture was tested on the Framingham, Pima Indians Diabetes, and Bank Marketing datasets, showing that enhanced privacy can be achieved without significantly compromising model accuracy.\"}]",1784179699,53,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":85,"head_meta":87,"extra_data":89,"updated_unix":27},"federated-learning-architecture-data-privacy-and-system-security-approaches","",{"@graph":35,"@context":84},[36,53,67],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/federated-learning-architecture-data-privacy-and-system-security-approaches/82331/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-16",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"How does the proposed approach enhance privacy in federated learning?","Question",{"text":74,"@type":75},"It combines homomorphic encryption to compute on encrypted data and differential privacy to prevent individual information extraction from model outputs.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"Why are model updates a privacy and security concern in federated learning?",{"text":79,"@type":75},"Because transmitted parameters can be analyzed by malicious actors, enabling model inference and data reconstruction attacks that may expose local sensitive information.",{"name":81,"@type":72,"acceptedAnswer":82},"What datasets were used to evaluate the architecture and what was the overall outcome?",{"text":83,"@type":75},"The architecture was tested on the Framingham, Pima Indians Diabetes, and Bank Marketing datasets, showing that enhanced privacy can be achieved without significantly compromising model accuracy.","https://schema.org",{"og:url":51,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":91},[92,96,100,104,109,114,119,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":45,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":45,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":45,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":45,"category_name":136,"show_sort_weight":105,"slug":137},19,"General","general"]