[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119821-en":3,"doc-seo-119821-105":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},119821,34359740700684,"Finn","https://ap-avatar.wpscdn.com/avatar/1f400023980c374ae676?_k=1777273430885731487",8,"Research & Report","Trustworthy Machine Learning Through the Lens of Privacy and Security - Dissertation Abstract","Trustworthy machine learning addresses real-world incidents caused by ML systems when deployed outside controlled settings. The work targets accurate but trustworthy models—explainable, privacy-preserving, secure, and robust—crucial for critical domains such as healthcare and finance. It tackles the difficult trade-off among utility, scalability, privacy, explainability, and security across paradigms including deep learning, centralized learning, and federated learning. The study presents novel privacy-preserving mechanisms that optimize utility and trustworthiness for natural language models, federated learning with human and mobile sensing, image classification, and explainable AI, providing practical deployment performance with marginal utility loss and rigorous theoretical guarantees.","New Jersey Institute of Technology  \nDigital Commons @ NJIT  \n\n| Dissertations | Electronic Theses and Dissertations |\n| --- | --- |\n| 5-31-2023\u003Cbr>Trustworthy machine learning through the lens of privacy and security\u003Cbr>Thi Kim Phung Lai\u003Cbr>New Jersey Institute of Technology, [phung08dt3@gmail.com](phung08dt3@gmail.com)\u003Cbr>Follow this and additional works at: [https://digitalcommons.njit.edu/dissertations](https://digitalcommons.njit.edu/dissertations)\u003Cbr> Part of the Data Science Commons, Information Security Commons, and the Theory and Algorithms Commons |  |\n\nRecommended Citation  \nLai, Thi Kim Phung, \"Trustworthy machine learning through the lens of privacy and security\" (2023) . Dissertations. 1664.  \n[https://digitalcommons.njit.edu/dissertations/1664](https://digitalcommons.njit.edu/dissertations/1664)  \nThis Dissertation is brought to you for free and open access by the Electronic Theses and Dissertations at Digital Commons @ NJIT. It has been accepted for inclusion in Dissertations by an authorized administrator of Digital Commons @ NJIT. For more information, please [contact digitalcommons@njit.edu](contact digitalcommons@njit.edu).  \nCopyright Warning & Restrictions  \nThe copyright law of the United States (Title 17, United States Code) governs the making of photocopies or other reproductions of copyrighted material.  \nUnder certain conditions specified in the law, libraries and archives are authorized to furnish a photocopy or other reproduction. One of these specified conditions is that the photocopy or reproduction is not to be “used for any purpose other than private study, scholarship, or research.”If a, user makes a request for, or later uses, a photocopy or reproduction for purposes in excess of “fair use” that user may be liable for copyright infringement,  \nThis institution reserves the right to refuse to accept a copying order if, in its judgment, fulfillment of the order would involve violation of copyright law.  \nPlease Note: The author retains the copyright while the New Jersey Institute of Technology reserves the right to distribute this thesis or dissertation  \nPrinting note: If you do not wish to print this page, then select“Pages from: first page \\# to: last page \\#” on the print dialog screen  \nThe Van Houten library has removed some of the personal information and all signatures from the approval page and biographical sketches of thesesand dissertations in order to protect the identity of NJIT graduates and faculty.  \nABSTRACT  \nTRUSTWORTHY MACHINE LEARNING  \nTHROUGH THE LENS OF PRIVACY AND SECURITY  \nby  \nThi Kim Phung Lai  \nNowadays, machine learning (ML) becomes ubiquitous and it is transforming society.  \nHowever, there are still many incidents caused by ML-based systems when ML is deployed in real-world scenarios. Therefore, to allow wide adoption of ML in the real world, especially in critical applications such as healthcare, finance, etc., it is crucial to develop ML models that are not only accurate but also trustworthy (e.g., explainable, privacy-preserving, secure, and robust) . Achieving trustworthy ML with different machine learning paradigms (e.g., deep learning, centralized learning, federated learning, etc.), and application domains (e.g., computer vision, natural language, human study, malware systems, etc.) is challenging, given the complicated trade-off among utility, scalability, privacy, explainability, and security. To bring trustworthy ML to real-world adoption with the trust of communities, this study makes a contribution of introducing a series of novel privacy-preserving mechanisms in which the trade-off between model utility and trustworthiness is optimized in different application domains, including natural language models, federated learning with human and mobile sensing applications, image classification, and explainable AI. The proposed mechanisms reach deployment levels of commercialized systems in real-world trials while providing trustworthiness with marginal util","cbCaiqIKk4tAIgS3","https://ap.wps.com/l/cbCaiqIKk4tAIgS3","pdf",11567105,1,252,"English","en",105,"# Abstract\n## Trust objectives: privacy, security, explainability, robustness\n## Challenges: utility–trust trade-offs and scalability\n## Contributions: privacy-preserving mechanisms across domains","[{\"question\":\"Why does the dissertation focus on trustworthy machine learning?\",\"answer\":\"Machine learning can cause incidents in real-world deployments, so adoption—especially in critical applications—requires models that remain accurate and trustworthy.\"},{\"question\":\"What aspects define “trustworthy” models in this work?\",\"answer\":\"Trustworthiness includes explainability, privacy-preserving properties, security, and robustness.\"},{\"question\":\"Which machine learning paradigms and application domains are covered?\",\"answer\":\"The study spans approaches such as deep learning, centralized learning, and federated learning, and it targets domains including natural language models, federated learning with sensing, image classification, and explainable AI.\"}]","Trustworthy Machine Learning Through the Lens of Privacy and Security - Dissertation Abstract | PDF",1785726492,635,{"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},"trustworthy-machine-learning-through-the-lens-of-privacy-and-security-dissertation-abstract","",{"@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/trustworthy-machine-learning-through-the-lens-of-privacy-and-security-dissertation-abstract/119821/",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},"Why does the dissertation focus on trustworthy machine learning?","Question",{"text":75,"@type":76},"Machine learning can cause incidents in real-world deployments, so adoption—especially in critical applications—requires models that remain accurate and trustworthy.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What aspects define “trustworthy” models in this work?",{"text":80,"@type":76},"Trustworthiness includes explainability, privacy-preserving properties, security, and robustness.",{"name":82,"@type":73,"acceptedAnswer":83},"Which machine learning paradigms and application domains are covered?",{"text":84,"@type":76},"The study spans approaches such as deep learning, centralized learning, and federated learning, and it targets domains including natural language models, federated learning with sensing, image classification, and explainable AI.","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"]