[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121630-en":3,"doc-seo-121630-105":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},121630,1099513958607,"Jiven","https://ap-avatar.wpscdn.com/avatar/100002390cf8733938c?x-image-process=image/resize,m_fixed,w_180,h_180&k=1778829742770036399",8,"Research & Report","HE-MAN - Homomorphically Encrypted MAchine learning with oNnx models","Machine learning algorithms enable valuable products and services, yet privacy and model confidentiality hinder sharing sensitive inputs and intellectual property with ML service providers. Fully homomorphic encryption (FHE) enables computation on encrypted data, but existing solutions remain difficult to integrate and often require cryptographic expertise or approximations of non-polynomial activations. HE-MAN is an open-source two-party toolset for privacy-preserving inference with ONNX models and homomorphically encrypted data. It hides cryptographic complexity and supports multiple ONNX models using Concrete and TenSEAL.","arXiv :2302 .08260v1 [ cs .CR] 16 Feb 2023  \nHE-MAN – Homomorphically Encrypted MAchine learning with  \noNnx models  \nMARTIN NOCKER∗ , MCI Management Center Innsbruck, Innsbruck, Austria DAVID DREXEL, MCI Management Center Innsbruck, Innsbruck, Austria MICHAEL RADER, Fraunhofer Austria Research GmbH, Wattens, Austria  \nALESSIO MONTUORO, SCCH Software Competence Center Hagenberg, Hagenberg, Austria PASCAL SCHÖTTLE, MCI Management Center Innsbruck, Innsbruck, Austria  \nMachine learning (ML) algorithms are increasingly important for the success of products and services, especially considering the growing amount and availability of data. This also holds for areas handling sensitive data, e.g. applications processing medical data or facial images. However, people are reluctant to pass their personal sensitive data to a ML service provider. Atthe same time, service providers have a strong interest in protecting their intellectual property and therefore refrain from publicly sharing their ML model. Fully homomorphic encryption (FHE) is a promising technique to enable individuals using ML services without giving up privacy and protecting the ML model of service providers at the same time. Despite steady improvements, FHE is still hardly integrated in today’s ML applications. Reasons for that are, among others, that existing implementations either require the user to possess expertise in FHE, do not feature an easy ML framework integration, or have to approximate non-polynomial activations.  \nWe introduce HE-MAN, an open-source two-party machine learning toolset for privacy preserving inference with ONNX models and homomorphically encrypted data. Both the model and the input data do not have to be disclosed. HE-MAN abstracts cryptographic details away from the users, thus expertise in FHE is not required for either party. HE-MAN’s security relies on its underlying FHE schemes. For now, we integrate two different homomorphic encryption schemes, namely Concrete and TenSEAL. Compared to prior work, HE-MAN supports a broad range of ML models in ONNX format out of the box without sacrificing accuracy.  \nWe evaluate the performance of our implementation on different network architectures classifying handwritten digits and performing face recognition and report accuracy and latency of the homomorphically encrypted inference. Cryptographic parameters are automatically derived by the tools. We show that the accuracy of HE-MAN is on par with models using plaintext input while inference latency is several orders of magnitude higher compared to the plaintext case.  \nCCS Concepts: • Security and privacy → Cryptography; Privacy protections; Public key encryption; • Computing methodologies → Neural networks.  \nAdditional Key Words and Phrases: Homomorphic Encryption, Machine Learning as a Service, Secure and Privacy-Preserving Machine Learning  \nACM Reference Format:  \nMartin Nocker, David Drexel, Michael Rader, Alessio Montuoro, and Pascal Schöttle. 2023. HE-MAN – Homomorphically Encrypted MAchine learning with oNnx models. In Proceedings of 2023 8th International Conference on Machine Learning Technologies (ICMLT) (ICMLT 2023). ACM, New York, NY, USA, 15 pages. [https://doi.org/10.1145/nnnnnnn.nnnnnnn](https://doi.org/10.1145/nnnnnnn.nnnnnnn)  \n1 INTRODUCTION  \nToday’s products and services increasingly benefit from the integration of evermore powerful machine learning (ML) algorithms. Furthermore, the amount and availability of data is steadily increasing and penetrates all kinds of areas of our daily lives. Thus, it comes as no surprise that also more and more personal data is collected and society as a whole could potentially benefit from the usage of this data in machine learning contexts. But, by definition, personal data is sensitive, thus, people are understandably reluctant to send this kind of data to, e.g. ML service providers. On the other hand, providers of Machine Learning as a Service (MLaaS) do not want to  \n∗ [Correspondence: martin","cbCaiaPtDoHEjqQN","https://ap.wps.com/l/cbCaiaPtDoHEjqQN","pdf",704197,1,15,"English","en",105,"# Introduction\n## Motivation and problem of MLaaS with sensitive data\n## Fully homomorphic encryption for encrypted inference\n## HE-MAN overview: two-party toolset and components\n## Evaluation approach and metrics","[{\"question\":\"Why do privacy concerns affect machine learning as a service (MLaaS)?\",\"answer\":\"People are reluctant to share personal sensitive data with ML service providers. At the same time, providers often avoid publicly disclosing their ML models because they protect intellectual property.\"},{\"question\":\"How does fully homomorphic encryption (FHE) help ML inference?\",\"answer\":\"FHE schemes allow computations on encrypted data without needing decryption between steps, enabling privacy-preserving inference on encrypted inputs.\"},{\"question\":\"What is HE-MAN and what does it integrate?\",\"answer\":\"HE-MAN is an open-source two-party toolset for privacy-preserving inference with ONNX models and homomorphically encrypted data. It integrates homomorphic encryption schemes such as Concrete and TenSEAL and supports ONNX models out of the box.\"}]","HE-MAN - Homomorphically Encrypted MAchine learning with oNnx models | PDF",1785805829,38,{"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},"he-man-homomorphically-encrypted-machine-learning-with-onnx-models","",{"@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/he-man-homomorphically-encrypted-machine-learning-with-onnx-models/121630/",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},"Why do privacy concerns affect machine learning as a service (MLaaS)?","Question",{"text":75,"@type":76},"People are reluctant to share personal sensitive data with ML service providers. At the same time, providers often avoid publicly disclosing their ML models because they protect intellectual property.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does fully homomorphic encryption (FHE) help ML inference?",{"text":80,"@type":76},"FHE schemes allow computations on encrypted data without needing decryption between steps, enabling privacy-preserving inference on encrypted inputs.",{"name":82,"@type":73,"acceptedAnswer":83},"What is HE-MAN and what does it integrate?",{"text":84,"@type":76},"HE-MAN is an open-source two-party toolset for privacy-preserving inference with ONNX models and homomorphically encrypted data. It integrates homomorphic encryption schemes such as Concrete and TenSEAL and supports ONNX models out of the box.","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"]