[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-128828-en":3,"doc-seo-128828-105":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},128828,2336474466712,"Maeve","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",6,"Technology","FHEMaLe-Framework for Homomorphic Encrypted Machine Learning","Machine learning relies on cloud computing for large-scale processing, but bandwidth constraints and network latency can limit real deployments. Edge computing reduces dependence on continuous connectivity and enables localized inference, yet privacy risks remain when sensitive data must be processed across cloud and edge. The proposed FHEMaLe framework enables machine learning computations directly on encrypted data via fully homomorphic encryption, avoiding decryption while revisiting complex ML operator steps to fit FHE processing requirements. It selects a CKKS-based cloud execution environment or a TFHE-based edge execution environment based on accuracy and platform preference, then partitions and distributes encrypted inference across an edge cluster to overcome single-device limitations.","1  \n2  \n3  \n4  \n5  \n6  \n7  \n8  \n9  \n10  \n11  \n12  \n13  \n14  \n15  \n16  \n17  \n18  \n19  \n20  \n21  \n22  \n23  \n24  \n25  \n26  \n27  \n28  \n29  \n30  \n31  \n32  \n33  \n34  \n35  \n36  \n37  \n38  \n39  \n40  \n41  \n42  \n43  \n44  \n45  \n46  \n47  \n48  \n49  \n50  \n51  \n52  \n53  \n54  \n55  \n56  \n57  \n58  \n59  \n60  \n61  \nFHEMaLe:Framework for Homomorphic Encrypted Machine Learning  \nB PRADEEP KUMAR REDDY, Indian Institute of Technology, India SAMEEKSHA GOYAL, Indian Institute of Technology, India RUCHIKA MEEL, Indian Institute of Technology, India  \nAYANTIKA CHATTERJEE, Indian Institute of Technology, India  \nMachine learning (ML) has revolutionized various industries by leveraging predictive models and data-driven insights, often relying on cloud computing for large-scale data processing. However, this dependence introduces challenges such as bandwidth constraints and network latency. Edge computing mitigates these issues by enabling localized processing, reducing reliance on continuous cloud connectivity, and optimizing resource allocation for dynamic workloads. Given the limited computational capacity of sensory nodes in ML systems, edge devices provide an effective solution by offloading processing tasks. However, a critical challenge in this paradigm is to ensure user privacy while handling sensitive data both in the cloud and in edge processing. To address this, we propose a Fully Homomorphic Encryption (FHE) enabled framework that enables ML computations directly on encrypted data, eliminating need for decryption. The main challenge to design such framework is that ML complex implementation steps need to be revisited with suitable optimizations to match FHE processing requirements. There are different standard libraries to support basic computation blocks on which encrypted ML processing is to be developed. These libraries vary in supported computation operators, computational complexity and memory demands. Those in-turn introduces latency and throughput challenges, especially on resource-constrained edge nodes. For example, in general HE library CKKS(Cheon-Kim-Kim-Song) with packing and approximate homomorphic operation support is known to be the best choice for privacy preserving AI algorithm implementation. However, analysis shows leveled CKKS is limited in implementing complex operators and hence not suitable for few specific ML algorithms like KNN, Logistic Regression or general activations in NN etc without any approximation. To avoid accuracy drops associated with approximations, Torus based FHE library (TFHE) can be a better choice to make certain ML implementations feasible. Moreover, our study shows compared to TFHE, CKKS with huge memory requirement is not suitable for resource constrained edge. Thus, underlying library choice to design such framework is crucial considering the trade-off between latency and accuracy. In this work, we propose an integrated framework FHEMaLe for encrypted ML processing which takes model architecture, desired accuracy, and platform preference as inputs and based on that appropriate execution environment is selected: a cloud platform leveraging the CKKS homomorphic encryption library or an edge platform using the TFHE library. Further, analysis shows the limitation of performing FHE ML on a single edge device and hence our framework partitions encrypted data, transmits it via a fabric API, and performs distributed encrypted ML computations across the edge cluster. We implement distributed ML inference for algorithms such as 􀀠-Nearest Neighbors (KNN) (Cloud CKKS=248 sec, Edge TFHE=37 min), Support Vector Machine (SVM) (Cloud CKKS=18 sec, Edge TFHE=4.15 min), and Logistic Regression (LR) ( Cloud CKKS=17 sec, Edge TFHE=7.82 min) on a cluster of 11 edge nodes. This work explains why KNN suffers from a major performance bottleneck in encrypted domain and may not be a great choice for encrypted ML processing. Furthermore, our encrypted operators are capable of supporting encrypted NN processing (Cloud CKKS= 57 s","cbCailpTkHIHU8XO","https://ap.wps.com/l/cbCailpTkHIHU8XO","pdf",1586825,5,1,26,"English","en",105,"# Introduction\n## Edge ML and privacy challenge\n## Proposed FHEMaLe framework\n## CKKS vs TFHE execution environments\n## Distributed encrypted inference","[{\"question\":\"What problem does FHEMaLe address in edge machine learning?\",\"answer\":\"FHEMaLe targets user privacy when sensitive data must be processed in both cloud and edge environments, where decryption is typically required otherwise.\"},{\"question\":\"How does the framework choose between CKKS and TFHE?\",\"answer\":\"It takes model architecture, desired accuracy, and platform preference as inputs, then selects a cloud platform using CKKS or an edge platform using TFHE based on the required latency–accuracy trade-off.\"},{\"question\":\"Why is distributed encrypted computation used instead of a single edge device?\",\"answer\":\"The study indicates limitations for performing FHE-based encrypted ML on a single edge device, so the framework partitions encrypted data, transmits it through an API, and executes distributed inference across an edge cluster.\"}]","FHEMaLe-Framework for Homomorphic Encrypted Machine Learning | PDF",1786003731,66,{"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},"fhemale-framework-for-homomorphic-encrypted-machine-learning","",{"@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/technology/",3,{"item":53,"name":13,"@type":44,"position":54},"https://docshare.wps.com/document/fhemale-framework-for-homomorphic-encrypted-machine-learning/128828/",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","2026-08-06",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},"What problem does FHEMaLe address in edge machine learning?","Question",{"text":77,"@type":78},"FHEMaLe targets user privacy when sensitive data must be processed in both cloud and edge environments, where decryption is typically required otherwise.","Answer",{"name":80,"@type":75,"acceptedAnswer":81},"How does the framework choose between CKKS and TFHE?",{"text":82,"@type":78},"It takes model architecture, desired accuracy, and platform preference as inputs, then selects a cloud platform using CKKS or an edge platform using TFHE based on the required latency–accuracy trade-off.",{"name":84,"@type":75,"acceptedAnswer":85},"Why is distributed encrypted computation used instead of a single edge device?",{"text":86,"@type":78},"The study indicates limitations for performing FHE-based encrypted ML on a single edge device, so the framework partitions encrypted data, transmits it through an API, and executes distributed inference across an edge cluster.","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},[95,99,103,107,111,114,119,124,129,132,136],{"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":20,"doc_module":4,"doc_module_name":47,"category_name":108,"show_sort_weight":109,"slug":110},"Comic",60,"comic",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":112,"slug":113},50,"technology",{"id":115,"doc_module":4,"doc_module_name":47,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":120,"doc_module":4,"doc_module_name":47,"category_name":121,"show_sort_weight":122,"slug":123},8,"Research & Report",30,"research-report",{"id":125,"doc_module":4,"doc_module_name":47,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":47,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":47,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":47,"category_name":138,"show_sort_weight":20,"slug":139},19,"General","general"]