[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119687-en":3,"doc-seo-119687-105":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},119687,1099513958607,"Jiven","https://ap-avatar.wpscdn.com/avatar/100002390cf8733938c?x-image-process=image/resize,m_fixed,w_180,h_180&k=1778829742770036399",8,"Research & Report","ezDPS - An Efficient and Zero-Knowledge Machine Learning Inference Pipeline","Machine Learning as a service (MLaaS) enables resource-limited clients to leverage cloud analytics, yet it creates integrity and privacy risks. The server may return unreliable outputs, and its private model parameters—also potentially trained on sensitive data—could be exposed during inference. By combining verifiable computation with zero-knowledge techniques, ezDPS builds a multi-stage zkML pipeline that executes multiple ML phases with established algorithms and custom proof gadgets. Experiments on real datasets show orders-of-magnitude efficiency gains over generic circuits while preserving stronger accuracy than single classification-based zkML approaches.","arXiv :2212 .05428v1 [ cs .CR] 11 Dec 2022  \nezDPS: An E􀀜cient and Zero-Knowledge Machine Learning  \nInference Pipeline∗  \nHaodi Wang† Thang Hoang‡  \nAbstract  \nMachine Learning as a service (MLaaS) permits resource-limited clients to access powerful data analytics services ubiquitously. Despite its merits, MLaaS poses signi􀀛cant concerns regarding the integrity of delegated computation and the privacy of the server's model parameters. To address this issue, Zhang et al. (CCS'20) initiated the study of zero-knowledge Machine Learning (zkML) . Few zkML schemes have been proposed afterward; however, they focus on sole ML classi􀀛cation algorithms that may not o􀀝er satisfactory accuracy or require large-scale training data and model parameters, which may not be desirable for some applications.  \nWe propose ezDPS, a new e􀀜cient and zero-knowledge ML inference scheme. Unlike prior works, ezDPS is a zkML pipeline in which the data is processed in multiple stages for high accuracy. Each stage of ezDPS is harnessed with an established ML algorithm that is shown to be e􀀝ective in various applications, including Discrete Wavelet Transformation, Principal Components Analysis, and Support Vector Machine. We design new gadgets to prove ML operations e􀀝ectively. We fully implemented ezDPS and assessed its performance on real datasets. Experimental results showed that ezDPS achieves one-to-three orders of magnitude more e􀀜cient than the generic circuit-based approach in all metrics while maintaining more desirable accuracy than single ML classi􀀛cation approaches.  \n1 Introduction  \nMachine learning (ML) has grown to become a game-changer for the humane society. A well-trained ML model can e􀀝ectively aid in performing highly complicated tasks such as medical diagnosis, natural language processing, intrusion detection, or 􀀛nancial forecasting. However, since a powerful ML model requires a large amount of data and computational resources for training, it may not be widely accessible to individuals or small organizations. To address this issue, Machine Learning as a Service (MLaaS) has been proposed, which permits resource-limited clients to access useful ML services (e.g., visualization, training, classi􀀛cation) o􀀝ered by cloud providers.  \nDespite its usefulness, MLaaS has posed new integrity and privacy concerns. When the client delegates the ML computation to the MLaaS server, it is not clear if she will receive a reliable response. A corrupted server may process the client data arbitrarily or even substitute it with malicious data, making the outcome untrustworthy. This is especially critical for sensitive applications such as medical diagnosis, intrusion detection, or fraud detection. Computation integrity can be addressed with Veri􀀛able Computation (VC), in which the MLaaS server attaches a proof to show that the computation  \n∗ This paper is to appear in Privacy-Enhancing Technologies Symposium (PETS) 2023 .†Beijing Normal University / Virginia Tech, [whd@mail.bnu.edu.cn](whd@mail.bnu.edu.cn).  \n‡Virginia Tech, [thanghoang@vt.edu](thanghoang@vt.edu).  \nis carried out correctly [19] . However, VC itself may not be su􀀜cient for MLaaS because it only enables computation integrity but not the privacy of the parameters used in the computation. In MLaaS, the server uses its private ML model to process the client data. This sophisticated model may cost signi􀀛cant resources to obtain and, therefore, it is considered the intellectual property of the server. Moreover, such models may also be trained from sensitive training data (e.g., medical) . As a result, it is undesirable that the MLaaS server leak any information about its private ML models when processing the client query.  \nThe above privacy concern inMLaaS can be addressed by adding the zero-knowledge property to the VC proof, which permits veri􀀛able computation without leaking any information other than the computation result [22] . Preliminary zero-knowledge VC (zkVC) protocols are comput","cbCaitjfaAcyyfvC","https://ap.wps.com/l/cbCaitjfaAcyyfvC","pdf",2251606,1,36,"English","en",105,"# Abstract\n# 1 Introduction\n## Background: MLaaS integrity and privacy concerns\n## Zero-knowledge and zkML inference overview\n## Motivation for zero-knowledge ML pipelines","[{\"question\":\"What core problem does ezDPS address in MLaaS?\",\"answer\":\"ezDPS addresses two risks in MLaaS: computation integrity when outsourcing inference and privacy leakage of the server’s model parameters during processing.\"},{\"question\":\"How does ezDPS differ from prior zkML approaches?\",\"answer\":\"Unlike earlier schemes that often focus on single final-phase classification, ezDPS is a multi-stage zkML inference pipeline where data is processed through multiple phases to improve accuracy.\"},{\"question\":\"What do the experiments show about ezDPS performance?\",\"answer\":\"Experiments on real datasets indicate ezDPS achieves one-to-three orders of magnitude better efficiency than a generic circuit-based approach, while maintaining more desirable accuracy than single ML classification approaches.\"}]","ezDPS - An Efficient and Zero-Knowledge Machine Learning Inference Pipeline | PDF",1785725757,91,{"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},"ezdps-an-efficient-and-zero-knowledge-machine-learning-inference-pipeline","",{"@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/ezdps-an-efficient-and-zero-knowledge-machine-learning-inference-pipeline/119687/",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","2026-08-03",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},"What core problem does ezDPS address in MLaaS?","Question",{"text":75,"@type":76},"ezDPS addresses two risks in MLaaS: computation integrity when outsourcing inference and privacy leakage of the server’s model parameters during processing.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does ezDPS differ from prior zkML approaches?",{"text":80,"@type":76},"Unlike earlier schemes that often focus on single final-phase classification, ezDPS is a multi-stage zkML inference pipeline where data is processed through multiple phases to improve accuracy.",{"name":82,"@type":73,"acceptedAnswer":83},"What do the experiments show about ezDPS performance?",{"text":84,"@type":76},"Experiments on real datasets indicate ezDPS achieves one-to-three orders of magnitude better efficiency than a generic circuit-based approach, while maintaining more desirable accuracy than single ML classification approaches.","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},[93,97,101,105,110,115,120,123,128,131,135],{"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":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]