[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-125809-en":3,"doc-seo-125809-105":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},125809,4398048949847,"Eliana","https://ap-avatar.wpscdn.com/avatar/400002536579ef2da7f?_k=1778318612642679267",8,"Research & Report","TOWARDS TRUSTWORTHY ARTIFICIAL INTELLIGENCE IN PRIVACY-PRESERVING COLLABORATIVE MACHINE LEARNING - Dissertation","Artificial Intelligence systems are increasingly used to simulate human intelligence and decision processes, yet their adoption—especially in high-risk settings such as autonomous systems and healthcare—raises concerns about societal impact and safety. This dissertation develops key concepts of trustworthy AI and identifies challenges across collaborative AI design, development, and deployment, resulting in concise developer guidelines. It further shows how privacy techniques like federated learning can enable collaboration without sharing private data while supporting trustworthy principles, assessing security under targeted poisoning, Byzantine-tolerant defenses, and potential regulatory compliance.","PhD-FSTM-2024-012  \nThe Faculty of Science, Technology and Medicine  \nDISSERTATION  \nDefence held on 04/03/2024 in Luxembourg  \nto obtain the degree of  \nDOCTEUR DE L’UNIVERSITÉ DU LUXEMBOURG  \nEN INFORMATIQUE  \nby  \nMary Katherine ROSZEL Born on 24 October 1993 in Florida, United States of America  \nTOWARDS TRUSTWORTHY ARTIFICIAL INTELLIGENCE IN PRIVACY-PRESERVING COLLABORATIVE MACHINE LEARNING  \nDissertation defence committee Dr. Radu STATE, dissertation supervisor Professor, Université du Luxembourg  \nDr. Gilbert FRIDGEN, Chairman Professor, Université du Luxembourg  \nDr. Vijay GURBANI, Vice Chairman  \nResearch Associate Professor, Illinois Institute of Technology / Chief Data Scientist, Vail Systems, Inc.  \nDr. Andrey MARTOVOY  \nSenior Advisor-Innovation & Digital, Association des Banques et Banquiers, Luxembourg (ABBL)  \nDr. Jean HILGER  \nHead of Finnovation Hub, Université du Luxembourg  \nTo my beloved husband  \nAcknowledgments  \nI would like to express my sincere gratitude to my supervisor Prof. Dr. Radu State for the opportunity to pursue my PhD and for the guidance and support during my studies. I appreciate his encouragement, guidance, and advice, especially during times of wavering motivation.  \nI would like to extend my appreciation to my CET members: Dr. Jean Hilger and Dr. Vijay Gurbani for providing their insights and constructive feedback. Further, I would like to express my appreciation to Prof. Dr. Gilbert Fridgen and Dr. Andrey Martovoy for agreeing to join my defense jury and taking the time to review my dissertation.  \nMy sincerest thanks are extended to Association des Banques et Banquiers, Luxembourg (ABBL) and its Fondation ABBL pour l’ducation !nancire for !nancially supporting my PhD and providing continuous input and facilitation of the project. Special thanks to Dr. Andrey Martovoy for his coordination and support throughout the duration of the project.  \nI would like to thank my colleagues in SEDAN lab for providing endless entertainment throughout the years. I would like to speci!cally extend my thanks to Dr. Beltran Fiz and Dr. Robert Norvill for all of their assistance in our research collaborations.  \nLastly, I want to thank my husband, Dr. Sean Rivera, for his never-ending support, countless hours spent discussing research, late nights working on papers together, and always believing in me. I could not have succeeded without him.  \nAbstract  \nArti!cial Intelligence (AI) systems are proliferating in our society due to their capacity to simulate human intelligence, behaviors, and processes. \"e increased utilization of AI systems in society, especially in high-risk se\\#ings such as autonomous systems and healthcare, has been accompanied by an increased concern about the impact of AI systems on society. In recent years, vulnerabilities to algorithmic bias, adversarial a\\#acks, and data breaches have resulted in the critical assessment of how AI systems can be designed to be inherently trustworthy.  \n\"is dissertation presents the key concepts of trustworthiness in AI systems, with a focus on identifying the challenges associated with designing, developing, and deploying collaborative AI. Towards this purpose, key elements of trustworthy AI are identi!ed, culminating in a set of concise guidelines that developers can leverage in the development of trustworthy AI. Further, this dissertation explores how techniques initially created solely for privacy, speci!cally federated learning, can be leveraged to build trust in machine-learning environments.  \nFederated learning is assessed for its implications on trustworthy principles, with a particular focus on how privacy is established to enable collaboration between participants without the sharing of private data. \"e security of federated learning is further assessed by demonstrating the impact of targeted model poisoning a\\#acks and an assessment of Byzantine-tolerant defense mechanisms to prevent and defend against such a\\#acks. Further, the potential ","cbCaipF7EY910j8o","https://ap.wps.com/l/cbCaipF7EY910j8o","pdf",6043954,1,186,"English","en",105,"# Introduction\n## Dissertation Structure\n## Contributions\n# Trustworthy Artificial Intelligence\n## Ethical and Regulatory Guidelines for Trustworthy AI\n## Trustworthy AI Concepts\n## The Role of Transparency\n# Establishing Requirements for Trustworthy AI\n## Related Work\n## Know Your Model (KYM)\n## Key Guidelines of KYM\n## Discussion and Future Work\n# Collaborative Learning: Leveraging Federated Learning to Increase Trust\n## Federated Learning\n## Federated Learning Use Cases\n## Case Study: Anti-Money Laundering\n## Challenges in Federated Learning\n## Implications on Trust\n# Defending Federated Learning\n## Background\n## Threat Model\n## Experiments\n## Experimental Results\n## Discussion & Conclusion\n# AI Regulation: Leveraging Federated Learning for the Artificial Intelligence Act\n## Introduction\n## Background\n## Federated Regulatory Sandbox","[{\"question\":\"What does the dissertation mean by “trustworthy AI” in collaborative machine learning?\",\"answer\":\"It focuses on identifying challenges in designing, developing, and deploying collaborative AI and defining key trustworthy AI elements, culminating in concise guidelines for developers.\"},{\"question\":\"How does the dissertation use federated learning to preserve privacy while enabling collaboration?\",\"answer\":\"It leverages privacy-oriented federated learning to establish privacy, allowing participants to collaborate without sharing private data.\"},{\"question\":\"How are the security risks of federated learning evaluated?\",\"answer\":\"The dissertation assesses security by demonstrating the impact of targeted model poisoning attacks and evaluating Byzantine-tolerant defense mechanisms to prevent and defend against such attacks.\"}]","TOWARDS TRUSTWORTHY ARTIFICIAL INTELLIGENCE IN PRIVACY-PRESERVING COLLABORATIVE MACHINE LEARNING - Dissertation | PDF",1785901325,469,{"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},"towards-trustworthy-artificial-intelligence-in-privacy-preserving-collaborative-machine-learning-dissertation","",{"@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/towards-trustworthy-artificial-intelligence-in-privacy-preserving-collaborative-machine-learning-dissertation/125809/",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","2026-08-05",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 does the dissertation mean by “trustworthy AI” in collaborative machine learning?","Question",{"text":75,"@type":76},"It focuses on identifying challenges in designing, developing, and deploying collaborative AI and defining key trustworthy AI elements, culminating in concise guidelines for developers.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the dissertation use federated learning to preserve privacy while enabling collaboration?",{"text":80,"@type":76},"It leverages privacy-oriented federated learning to establish privacy, allowing participants to collaborate without sharing private data.",{"name":82,"@type":73,"acceptedAnswer":83},"How are the security risks of federated learning evaluated?",{"text":84,"@type":76},"The dissertation assesses security by demonstrating the impact of targeted model poisoning attacks and evaluating Byzantine-tolerant defense mechanisms to prevent and defend against such attacks.","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"]