[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-127735-en":3,"doc-seo-127735-105":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},127735,962084926284,"Aurora","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","Confidential and Verifiable Machine Learning Delegations on the Cloud","Cloud computing enables users to outsource storage and computation to affordable servers, yet it raises critical risks around data confidentiality and computation integrity when cloud providers cannot be trusted. A confidential and verifiable delegation scheme is proposed by combining secure multiparty computation with zero-knowledge proofs. Secret-shared data and outsourced computations remain private if at least one MPC server is honest, while verification stays correct even under all-malicious servers. Efficient interactive proofs are designed, including an optimized protocol for matrix multiplication and performance evaluation on neural-network inference.","Confidential and Verifiable Machine Learning Delegations on the Cloud  \nWenxuan Wu Texas A&M University  \nSoamar Homsi  \nUS Air Force Research Laboratory Information Warfare Division  \nYupeng Zhang University of Illinois Urbana-Champaign  \nABSTRACT  \nWith the growing adoption of cloud computing, the ability to store data and delegate computations to powerful and affordable cloud servers have become advantageous for both companies and individual users. However, the security of cloud computing has emerged asa significant concern. Particularly, Cloud Service Providers (CSPs) cannot assure data confidentiality and computations integrity in mission-critical applications. In this paper, we propose a confidential and verifiable delegation scheme that advances and overcomes major performance limitations of existing Secure Multiparty Computation (MPC) and Zero Knowledge Proof (ZKP) . Secret-shared Data and delegated computations to multiple cloud servers remain completely confidential as long as there is at least one honest MPC server. Moreover, results are guaranteed to be valid even if all the participating servers are malicious. Specifically, we design an efficient protocol based on interactive proofs, such that most of the computations generating the proof can be done locally on each server. In addition, we propose a special protocol for matrix multiplication where the overhead of generating the proof is asymptotically smaller than the time to evaluate the result in MPC. Experimental evaluation demonstrates that our scheme significantly outperforms prior work, with the online prover time being 1-2 orders of magnitude faster. Notably, in the matrix multiplication protocol, only a minimal 2% of the total time is spent on the proof generation. Furthermore, we conducted tests on machine learning inference tasks. We executed the protocol for a fully-connected neural network with 3 layers on the MNIST dataset and it takes 2.6 seconds to compute the inference in MPC and generate the proof, 88× faster than prior work. We also tested the convolutional neural network of Lenet with 2 convolution layers and 3 dense layers and the running time is less than 300 seconds across three servers. 1  \nKEYWORDS  \nZero-Knowledge Proof, Privacy-preserving Machine Learning, Secure Multiparty Computations  \n1 INTRODUCTION  \nCloud computing has revolutionized the way organizations, businesses and individuals store, access, and process data. Rather than relying on traditional data centers that are centralized, expensive to setup, and costly to maintain and run, cloud computing offers a remote access to unlimited resources available on demand over the internet. Although cloud computing has numerous advantages, including elasticity, scalability, and cost savings, it comes with major  \n1Approved for Public Release on 16 March 2024; Distribution Is Unlimited; Case Number: AFRL-2024-1294 .  \nFigure 1: Confidential and Verifiable Delegation.  \ncybersecurity risks and concerns. Specifically, they require end-toend confidentiality of the data, meaning that the data should remain confidential from Cloud Services Providers (CSPs) and the integrity of the data and computations, meaning that the data and results should be valid even if the cloud servers are compromised. For example, governmental agencies procure cloud services based on compliance with specified standards that must be established as a trusted entity in providing secure services. Although the processes for meeting these standards are costly and time-consuming, they still cannot provide any mathematically-grounded assurances on data and computation security. In this paper, we aim to leverage widely available commercial CSPs without any dependence on their trustworthiness or security measures.  \nWe thus seek to address the limitations of the state ofthe art applied cryptographic methods and to build the necessary building blocks that enable the development of secure and efficient applications such as Machine","cbCaisL34V1oFsNs","https://ap.wps.com/l/cbCaisL34V1oFsNs","pdf",835742,6,1,14,"English","en",105,"# Abstract\n# Introduction\n## Threat model and security guarantees\n# Scheme overview and protocol flow\n# Comparison with existing schemes","[{\"question\":\"How does the scheme keep data and ML models confidential when delegating to cloud servers?\",\"answer\":\"The user secret-shares the data and the cloud servers run MPC so that data and the model stay confidential as long as at least one MPC server is honest.\"},{\"question\":\"What ensures that outsourced ML prediction results are verifiable?\",\"answer\":\"Cloud servers generate a zero-knowledge proof (ZKP) using an MPC-based protocol, and the user reconstructs and verifies the final result.\"},{\"question\":\"How does the proposed approach handle malicious servers?\",\"answer\":\"Security guarantees hold even if all participating servers behave maliciously, with result validity still guaranteed via the proof system.\"}]","Confidential and Verifiable Machine Learning Delegations on the Cloud | PDF",1785941326,35,{"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},"confidential-and-verifiable-machine-learning-delegations-on-the-cloud","",{"@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/confidential-and-verifiable-machine-learning-delegations-on-the-cloud/127735/",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","2026-08-24","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},"How does the scheme keep data and ML models confidential when delegating to cloud servers?","Question",{"text":77,"@type":78},"The user secret-shares the data and the cloud servers run MPC so that data and the model stay confidential as long as at least one MPC server is honest.","Answer",{"name":80,"@type":75,"acceptedAnswer":81},"What ensures that outsourced ML prediction results are verifiable?",{"text":82,"@type":78},"Cloud servers generate a zero-knowledge proof (ZKP) using an MPC-based protocol, and the user reconstructs and verifies the final result.",{"name":84,"@type":75,"acceptedAnswer":85},"How does the proposed approach handle malicious servers?",{"text":86,"@type":78},"Security guarantees hold even if all participating servers behave maliciously, with result validity still guaranteed via the proof system.","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},[95,99,103,107,112,116,121,124,129,132,136],{"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":108,"doc_module":4,"doc_module_name":47,"category_name":109,"show_sort_weight":110,"slug":111},5,"Comic",60,"comic",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":113,"show_sort_weight":114,"slug":115},"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":47,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":122,"slug":123},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":108,"slug":139},19,"General","general"]