[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118747-en":3,"doc-seo-118747-105":30,"detail-sidebar-cat-0-en-105":84},{"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":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},118747,1099513958762,"Logic","https://ap-avatar.wpscdn.com/avatar/1000023916a998db790?x-image-process=image/resize,m_fixed,w_180,h_180&k=1784791008015729253",8,"Research & Report","Privacy-Preserving Machine Learning for Healthcare - Open Challenges and Future Perspectives - Review","Machine Learning (ML) is increasingly used for healthcare prediction tasks such as diagnosis, prognosis, and treatment planning, but medical data sensitivity demands privacy protection across the entire ML lifecycle. The review surveys Privacy-Preserving Machine Learning (PPML) methods for healthcare, emphasizing privacy-preserving training and inference-as-a-service. It synthesizes recent trends, analyzes key challenges, and outlines future research opportunities to support private, efficient models suitable for trustworthy real-world healthcare deployment.","arXiv :2303 . 15563v1 [ cs .LG] 27 Mar 2023  \nICLR 2023 Workshop on Trustworthy Machine Learning for Healthcare   \nPRIVACY-PRESERVING MACHINE LEARNING FOR HEALTHCARE: OPEN CHALLENGES AND FUTURE PERSPECTIVES  \nAlejandro Guerra-Manzanares􀀃, L. Julian Lechuga Lopez􀀃 , Michail Maniatakos and Farah E. Shamout  \nDepartment of Computer Engineering, New York University Abu Dhabi {ag9454, ljl5178, mm6446, [fs999](fs999}@nyu.edu)[}](fs999}@nyu.edu)[@nyu.edu](fs999}@nyu.edu)  \nABSTRACT  \nMachine Learning (ML) has recently shown tremendous success in modeling various healthcare prediction tasks, ranging from disease diagnosis and prognosis to patient treatment. Due to the sensitive nature of medical data, privacy must be considered along the entire ML pipeline, from model training to inference. In this paper, we conduct a review of recent literature concerning Privacy-Preserving Machine Learning (PPML) for healthcare. We primarily focus on privacy-preserving training and inference-as-a-service, and perform a comprehensive review of existing trends, identify challenges, and discuss opportunities for future research directions. The aim of this review is to guide the development of private and ef-􀀂cient ML models in healthcare, with the prospects of translating research efforts into real-world settings.  \n1 INTRODUCTION  \nMachine Learning (ML) and Deep Learning (DL) have shown great promise in many domains, leveraging the use of large datasets. Some notable contributions include AlphaFold (Jumper et al., 2021) for the prediction of protein structures and Transformers (Vaswani et al., 2017) for natural language processing. Healthcare is one of the domains in which ML is expected to provide substantial improvements in the delivery of patient care worldwide (WHO, 2021) . Given the rapid growth in the number of models over the last couple of years (Rav􀀞􀀑 et al., 2016; Miotto et al., 2018; Kaul et al., 2022; Javaid et al., 2022), healthcare applications deserve special consideration considering the sensitive nature of the data that is required to train the models and the safety-critical nature of medical decision-making.  \nIn this regard, real-world implementation of such models is still hampered by ethical and legal constraints. Legal frameworks have been developed and enforced to guarantee the transparency and privacy of ML-based healthcare solutions, such as the Health Insurance Portability and Accountability Act (HIPAA) in the United States (Gostin et al., 2009) and the General Data Protection Regulation (GDPR) in Europe (Voigt & Von dem Bussche, 2017) . Therefore, there is a crucial need for Privacy-Preserving Machine Learning (PPML) in healthcare to enable the implementation of trustworthy systems in the future. The main goal of this review is to provide a comprehensive overview of state-of-the-art PPML in healthcare and encourage the development of new methodologies that tackle speci􀀂c challenges relevant to the nature of the domain.  \nMotivation. There exist several related literature reviews that focus on a speci􀀂c subset of PPML for healthcare. Several highlight recent advancements in federated learning (Xu et al., 2021; Ali et al., 2022; Joshi et al., 2022; Nguyen et al., 2022), cryptographic techniques (Zalonis et al., 2022), or security aspects of ML models, such as adversarial attacks (Liu et al., 2021) . Existing review articles cover a wide range of applications related to health and input data modalities, ranging from IoT sensors to medical images (Qayyum et al., 2020) . Compared to existing work, our review has three main contributions with the intent of bridging between research pertaining to ML for healthcare and cybersecurity. First, we distinguish between PPML for training and inference, i.e., ML-as-a-service.  \n􀀃 Equal contributions.  \nICLR 2023 Workshop on Trustworthy Machine Learning for Healthcare   \nSecond, we focus on state-of-the-art (SOTA) literature published in the last three years, considering the high proliferati","cbCaiscxy8GpTE6x","https://ap.wps.com/l/cbCaiscxy8GpTE6x","pdf",214375,1,13,"English","en",105,"# Introduction\n## Motivation\n# Privacy-Preserving Machine Learning: Background & Terminology\n## Federated Learning\n# State of the Art for Privacy-Preserving ML\n## PPML for Training\n## PPML for Inference\n# Open Challenges and Future Directions\n# Concluding Remarks","[{\"question\":\"Which inclusion criteria does the review use for selecting studies?\",\"answer\":\"It includes recent work from 2020 onward and focuses on PPML methods for training and/or inference, covering clinical tasks using medical images and/or electronic health records (EHR).\"}]","Privacy-Preserving Machine Learning for Healthcare - Open Challenges and Future Perspectives - Review | PDF",1785720033,33,{"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":79,"head_meta":81,"extra_data":83,"updated_unix":28},"privacy-preserving-machine-learning-for-healthcare-open-challenges-and-future-perspectives-review","",{"@graph":36,"@context":78},[37,54,69],{"@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/privacy-preserving-machine-learning-for-healthcare-open-challenges-and-future-perspectives-review/118747/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04","2026-08-03",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72],{"name":73,"@type":74,"acceptedAnswer":75},"Which inclusion criteria does the review use for selecting studies?","Question",{"text":76,"@type":77},"It includes recent work from 2020 onward and focuses on PPML methods for training and/or inference, covering clinical tasks using medical images and/or electronic health records (EHR).","Answer","https://schema.org",{"og:url":52,"og:type":80,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":82,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":85},[86,90,94,98,103,108,113,116,121,124,128],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":87,"show_sort_weight":88,"slug":89},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":91,"show_sort_weight":92,"slug":93},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Exam",70,"exam",{"id":99,"doc_module":4,"doc_module_name":46,"category_name":100,"show_sort_weight":101,"slug":102},5,"Comic",60,"comic",{"id":104,"doc_module":4,"doc_module_name":46,"category_name":105,"show_sort_weight":106,"slug":107},6,"Technology",50,"technology",{"id":109,"doc_module":4,"doc_module_name":46,"category_name":110,"show_sort_weight":111,"slug":112},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":114,"slug":115},30,"research-report",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":118,"show_sort_weight":119,"slug":120},9,"Religion & Spirituality",20,"religion-spirituality",{"id":119,"doc_module":4,"doc_module_name":46,"category_name":122,"show_sort_weight":119,"slug":123},"World Cup","world-cup",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":126,"show_sort_weight":125,"slug":127},10,"Lifestyle","lifestyle",{"id":129,"doc_module":4,"doc_module_name":46,"category_name":130,"show_sort_weight":99,"slug":131},19,"General","general"]