[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-123666-en":3,"doc-seo-123666-105":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},123666,962075006959,"Anda","https://ap-avatar.wpscdn.com/avatar/e0002397efbe92a78e?_k=1776741047341049297",6,"Technology","Secure and Private Access to Machine Learning Models via Cloud-based Execution Platform","Machine learning (ML) models for different purposes can be offered through cloud-based execution platforms. In such deployments, the data owner, the model provider, and the execution platform may be separate entities, requiring trust to support secure and private usage. The disclosure describes a verifiable execution platform authenticated by the data owner using confidential computing and/or trusted execution environments. It executes a requested ML model on encrypted data so the user can obtain inference results while the model provider cannot access user data and the data owner does not access the model.","Technical Disclosure Commons  \nDefensive Publications Series  \nApril 2023  \nSecure and Private Access to Machine Learning Models via Cloud-based Execution Platform  \nJérôme Glisse  \nFollow this and additional works at: [https://www.tdcommons.org/dpubs_series](https://www.tdcommons.org/dpubs_series)  \nRecommended Citation  \nGlisse, Jérôme, \"Secure and Private Access to Machine Learning Models via Cloud-based Execution Platform\", Technical Disclosure Commons,(April 26, 2023)  \n[https://www.tdcommons.org/dpubs_series/5845](https://www.tdcommons.org/dpubs_series/5845)  \nThis work is licensed under a Creative Commons Attribution 4.0 License.  \nThis Article is brought to you for free and open access by Technical Disclosure Commons. It has been accepted for inclusion in Defensive Publications Series by an authorized administrator of Technical Disclosure Commons.  \nSecure and Private Access to Machine Learning Models via Cloud-based Execution  \nPlatform  \nABSTRACT  \nMachine learning (ML) models for various purposes may be made available via cloud  \nbased execution platforms. The data owner, the model provider, and the execution platform  \nwhere a model is deployed may be different entities. In this configuration, it is necessary to  \nestablish trust between the model provider, the execution platform, and the user to enable secure and private use of machine learning models. This disclosure describes an execution platform that  \ncan be verified and authenticated by a data owner as a model provider using techniques such as  \nconfidential computing and/or trusted execution environment. The execution platform enables  \nthe model provider to make their models available for use by data owners. Data owners can  \nprovide encrypted data to the execution platform and specify a ML model to be applied to the  \ndata. The execution platform implements an instance of the ML model and enables secure access  \nto the user data without the model provider being able to access the data. Thus, users can obtain  \nthe benefit of using a ML model of their choice via the execution platform and model providers  \ncan provide models in a secure marketplace, while preserving the privacy and security for both  \nentities.  \nKEYWORDS  \n● Confidential computing  \n● Trusted execution environment  \n● Secure enclave  \n● Machine learning marketplace  \n● Data privacy  \n● Model confidentiality  \nPublished by Technical Disclosure Commons, 2023 2  \nBACKGROUND  \nMachine learning models can be used for a variety of tasks such as email spam filtering, image classification, etc. To perform tasks such as spam filtering or image classification, the emails or images are provided to the model. Models for various purposes may be made available by different entities. Many machine learning tasks are performed on cloud-based execution platforms. In current applications of machine learning models, the data owner (user), the model provider, and the execution platform where a model is deployed (e.g., a cloud computing provider) may thus be different entities. In this configuration, it is necessary to establish trust between the model provider, the execution platform, and the user to enable the user to utilize machine learning models.  \nDESCRIPTION  \nThis disclosure describes techniques to allow an entity (e.g., a model provider) to provide another, separate entity (e.g., an execution platform) with access to a machine learning model, without the model provider getting access to user data to be processed by the model, and without the data owner getting access to the model.  \nFig. 1: Secure and Private Access to Machine Learning Models via Execution Platform  \n[https://www.tdcommons.org/dpubs_series/5845](https://www.tdcommons.org/dpubs_series/5845) 3  \nFig. 1 illustrates an example method to automatically provide access to machine learning models via an execution platform (e.g., hosted by a cloud computing provider) to end users while preserving user privacy. A model provider (102) makes one ","cbCaiuFUHQAC8Cjo","https://ap.wps.com/l/cbCaiuFUHQAC8Cjo","pdf",147007,1,7,"English","en",105,"# Abstract\n# Background\n# Description\n## Secure execution platform workflow","[{\"question\":\"What problem does the disclosure address about machine learning model deployment in the cloud?\",\"answer\":\"Different entities may play the roles of data owner, model provider, and cloud execution platform. Trust is needed to use models securely and privately across these separate parties.\"},{\"question\":\"How can the execution platform be verified and authenticated in the proposed approach?\",\"answer\":\"The data owner authenticates and verifies the execution platform using techniques such as confidential computing and/or trusted execution environments.\"},{\"question\":\"How are encrypted user data and model confidentiality handled during execution?\",\"answer\":\"Encrypted data is provided to a secure execution enclave where the ML model runs. Results are accessible only to the user, preventing the model provider from accessing the user data while also keeping the model from being revealed to the user.\"}]","Secure and Private Access to Machine Learning Models via Cloud-based Execution Platform | PDF",1785817912,18,{"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-and-private-access-to-machine-learning-models-via-cloud-based-execution-platform","",{"@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/technology/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/secure-and-private-access-to-machine-learning-models-via-cloud-based-execution-platform/123666/",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","2026-08-04",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 problem does the disclosure address about machine learning model deployment in the cloud?","Question",{"text":75,"@type":76},"Different entities may play the roles of data owner, model provider, and cloud execution platform. Trust is needed to use models securely and privately across these separate parties.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How can the execution platform be verified and authenticated in the proposed approach?",{"text":80,"@type":76},"The data owner authenticates and verifies the execution platform using techniques such as confidential computing and/or trusted execution environments.",{"name":82,"@type":73,"acceptedAnswer":83},"How are encrypted user data and model confidentiality handled during execution?",{"text":84,"@type":76},"Encrypted data is provided to a secure execution enclave where the ML model runs. Results are accessible only to the user, preventing the model provider from accessing the user data while also keeping the model from being revealed to the user.","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},[93,97,101,105,110,113,117,122,127,130,134],{"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":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":111,"slug":112},50,"technology",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":114,"show_sort_weight":115,"slug":116},"Healthcare",40,"healthcare",{"id":118,"doc_module":4,"doc_module_name":46,"category_name":119,"show_sort_weight":120,"slug":121},8,"Research & Report",30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]