[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-117142-en":3,"doc-seo-117142-105":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},117142,549758252649,"Ivy","https://ap-avatar.wpscdn.com/avatar/8000253669c5317157?_k=1778319167496531819",8,"Research & Report","Data Privacy and Valuation for Trustworthy Machine Learning","Widespread data collection, combined with downstream use beyond the control of original contributors, has intensified ethical concerns surrounding machine learning. This thesis studies two intertwined issues: the privacy of individuals’ data and the value of that data within trustworthy machine learning. It presents efficient methods for accurate data valuation using properties of machine learning algorithms, and addresses privacy risks by analyzing attack severity and improving attacker calibration. It also develops differentially private approaches with improved privacy-utility trade-offs and pruning to reduce inefficiencies.","This thesis has been submitted in fulfilment of the requirements for a postgraduate degree (e. g. PhD, MPhil, DClinPsychol) at the University of Edinburgh. Please note the following terms and conditions of use:  \n• This work is protected by copyright and other intellectual property rights, which are retained by the thesis author, unless otherwise stated.  \n• A copy can be downloaded for personal non-commercial research or study, without prior permission or charge.  \n• This thesis cannot be reproduced or quoted extensively from without first obtaining permission in writing from the author.  \n• The content must not be changed in any way or sold commercially in any format or medium without the formal permission of the author.  \n• When referring to this work, full bibliographic details including the author, title, awarding institution and date of the thesis must be given.  \nData Privacy and Valuation for Trustworthy  \nMachine Learning  \nLauren Watson  \nU  \nR  \nG  \nH  \nO  \nF  \nE  \nD  \nDoctor of Philosophy  \nLaboratory for Foundations of Computer Science School of Informatics  \nUniversity of Edinburgh  \nAbstract  \nWidespread data collection-and the subsequent use of this data beyond the control of the original data contributors-has become a fact of modern life. The recent excitement caused by impressive applications of machine learning models is thus tempered by growing concern about their ethical impact. In this thesis, we examine two particular ethical aspects of the machine learning process: the privacy and value of an individual’s data, and their subtle relationship to effectively training machine learning models. Accurate valuation of data has several important applications, including allowing individuals to be fairly compensated for their contributions and enabling resource efficient machine learning. However, the current state-of-the-art data valuation techniques are highly computationally expensive, even to approximate. We introduce techniques exploiting the theoretical properties of machine learning algorithms to efficiently evaluate the impact of individual datapoints on machine learning models without sacrificing accuracy. On the other hand, in data privacy it has become apparent that machine learning models and statistical analyses risk the privacy of their underlying datasets. Even when only the result of the analysis is released and the data is not publicly available. This has led to two key directions of work in the data privacy community: the development of attacks demonstrating the privacy risks of machine learning models, and the proposal of privacy protection approaches. In the area of privacy attacks, we examine the severity of privacy risks posed by machine learning models to individual data contributors. We demonstrate how to improve attacker efficacy by calibrating attacks to include the typical model behaviour with respect to a given point. In privacy protection, we propose techniques based on intuitive privacy approaches and the properties of the stochastic gradient descent algorithm. We provably provide differential privacy, the current gold standard privacy guarantee, while improving the privacy-utility trade-off for machine learning and statistical attack detection. We then investigate the inefficiencies of the differentially private stochastic gradient descent learning algorithm, and propose pruning as a way to alleviate these challenges.  \nLay Summary  \nThe decisions of machine learning algorithms increasingly effect our daily lives. At times, their capabilities can be awe-inspiring. For example, their ability to analyse complex trends has many useful applications. However, these algorithms are ultimately built on data. Consequently, computers at our banks, doctor’s offices, schools and workplaces-not to mention those in our pockets-now collect vast amounts of our personal data daily. In this thesis, we address how data can be at risk when used to train machine learning models, and propose ways to mitigate th","cbCaiu2nbVFCxlbf","https://ap.wps.com/l/cbCaiu2nbVFCxlbf","pdf",9236235,1,180,"English","en",105,"# Abstract\n# Lay Summary\n# Acknowledgements","[{\"question\":\"What ethical aspects of machine learning does the thesis focus on?\",\"answer\":\"The thesis focuses on data privacy and the valuation of an individual’s data, and how these issues subtly relate to effectively training machine learning models.\"},{\"question\":\"Why is data valuation important in the thesis?\",\"answer\":\"Accurate valuation supports fair compensation of data contributors and enables resource-efficient machine learning, while existing techniques are too computationally expensive to approximate.\"},{\"question\":\"How does the thesis address privacy risks in machine learning?\",\"answer\":\"It examines privacy attacks and proposes protections, including techniques based on intuitive privacy ideas and the stochastic gradient descent algorithm, providing differential privacy with improved privacy-utility trade-offs.\"}]","Data Privacy and Valuation for Trustworthy Machine Learning | PDF",1785674085,454,{"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},"data-privacy-and-valuation-for-trustworthy-machine-learning","",{"@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/data-privacy-and-valuation-for-trustworthy-machine-learning/117142/",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","2026-08-02",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 ethical aspects of machine learning does the thesis focus on?","Question",{"text":75,"@type":76},"The thesis focuses on data privacy and the valuation of an individual’s data, and how these issues subtly relate to effectively training machine learning models.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Why is data valuation important in the thesis?",{"text":80,"@type":76},"Accurate valuation supports fair compensation of data contributors and enables resource-efficient machine learning, while existing techniques are too computationally expensive to approximate.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the thesis address privacy risks in machine learning?",{"text":84,"@type":76},"It examines privacy attacks and proposes protections, including techniques based on intuitive privacy ideas and the stochastic gradient descent algorithm, providing differential privacy with improved privacy-utility trade-offs.","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"]