<?xml version='1.0' encoding='UTF-8'?><?xml-stylesheet href='static/style.xsl' type='text/xsl'?><OAI-PMH xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/ http://www.openarchives.org/OAI/2.0/OAI-PMH.xsd"><responseDate>2026-11-22T10:52:18Z</responseDate><request verb="GetRecord" identifier="oai:ecommons.cornell.edu:1813/114569" metadataPrefix="dim">https://ecommons.cornell.edu/server/oai/request</request><GetRecord><record><header><identifier>oai:ecommons.cornell.edu:1813/114569</identifier><datestamp>2026-05-15T19:46:23Z</datestamp><setSpec>com_1813_35</setSpec><setSpec>col_1813_47</setSpec></header><metadata><dim:dim xmlns:dim="http://www.dspace.org/xmlns/dspace/dim" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:doc="http://www.lyncode.com/xoai" xsi:schemaLocation="http://www.dspace.org/xmlns/dspace/dim http://www.dspace.org/schema/dim.xsd">
   <dim:field mdschema="dc" element="contributor" qualifier="author">Bagdasaryan, Eugene</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="chair" lang="en_US">Shmatikov, Vitaly</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="committeeMember" lang="en_US">Estrin, Deborah</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="committeeMember" lang="en_US">Belongie, Serge</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="committeeMember" lang="en_US">Lee, Clarence</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="accessioned">2024-04-05T18:46:06Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="available">2024-04-05T18:46:06Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="issued">2023-08</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="other">ProQuest Submission ID: 13889</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="other">ProQuest Publication ID: 30575621</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="uri">https://hdl.handle.net/1813/114569</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="doi">https://doi.org/10.7298/21m1-3k83</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="bibid">16219353</dim:field>
   <dim:field mdschema="dc" element="description" lang="en_US">260 pages</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="abstract" lang="en_US">Machine learning methods have become a commodity in the toolkits of both researchers and practitioners. For performance and privacy reasons, new applications often rely on third-party code or pretrained models, train on crowd-sourced data, and sometimes move learning to users’ devices. This introduces vulnerabilities such as backdoors, i.e., unrelated tasks that the model may unintentionally learn when an adversary controls parts of the training data or pipeline. In this thesis, we identify new threats to ML models and propose approaches that balance security, accuracy, and privacy without disruptive changes to the existing training infrastructures.</dim:field>
   <dim:field mdschema="dc" element="language" qualifier="iso">en</dim:field>
   <dim:field mdschema="dc" element="rights" lang="*">Attribution 4.0 International</dim:field>
   <dim:field mdschema="dc" element="rights" qualifier="uri" lang="*">https://creativecommons.org/licenses/by/4.0/</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">machine learning</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">security and privacy</dim:field>
   <dim:field mdschema="dc" element="title" lang="en_US">(Un)Trustworthy Machine Learning</dim:field>
   <dim:field mdschema="dc" element="type" lang="en_US">dissertation or thesis</dim:field>
   <dim:field mdschema="dc" element="relation" qualifier="localuri">https://newcatalog.library.cornell.edu/catalog/16219353</dim:field>
   <dim:field mdschema="dc" element="format" qualifier="mimetype">application/pdf</dim:field>
   <dim:field mdschema="thesis" element="degree" qualifier="discipline">Computer Science</dim:field>
   <dim:field mdschema="thesis" element="degree" qualifier="grantor">Cornell University</dim:field>
   <dim:field mdschema="thesis" element="degree" qualifier="level">Doctor of Philosophy</dim:field>
   <dim:field mdschema="thesis" element="degree" qualifier="name">Ph. D., Computer Science</dim:field>
   <dim:field mdschema="dcterms" element="license">https://hdl.handle.net/1813/59810.2</dim:field>
   <dim:field mdschema="dspace" element="entity" qualifier="type">Publication</dim:field>
   <dim:field mdschema="cris" element="virtual" qualifier="collection" authority="https://cornell-ecommons.eks.prod.4science.cloud/handle/1813/47" confidence="600">Cornell Theses and Dissertations</dim:field>
   <dim:field mdschema="cris" element="virtual" qualifier="author">Bagdasaryan, Eugene</dim:field>
   <dim:field mdschema="cris" element="virtualsource" qualifier="collection">5893a6ea-7af3-41d7-abc6-04bcd26ab5df</dim:field>
   <dim:field mdschema="others" element="access-status">open.access</dim:field>
   <dim:field mdschema="others" element="access-status">open.access</dim:field>
   <dim:field mdschema="cerif" element="openaire" authority="" confidence="-1">&lt;Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="b1bc5c7e-af90-4d85-9eae-01fbdb6307f0">
	&lt;Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843&lt;/Type>
	&lt;Language>en&lt;/Language>
   	&lt;Title>(Un)Trustworthy Machine Learning&lt;/Title>
   	&lt;PublishedIn>
    	&lt;Publication>
      	&lt;/Publication>
   	&lt;/PublishedIn>
   	&lt;PublicationDate>2023-08&lt;/PublicationDate>
   	&lt;DOI>https://doi.org/10.7298/21m1-3k83&lt;/DOI>
   	&lt;Authors>
      	&lt;Author>
        	&lt;DisplayName>Bagdasaryan, Eugene&lt;/DisplayName>
         	&lt;Affiliation>
         		&lt;OrgUnit>
         		&lt;/OrgUnit>
         	&lt;/Affiliation>
      	&lt;/Author>
	&lt;/Authors>
   	&lt;Editors>
	&lt;/Editors>
    &lt;Publishers>
        &lt;Publisher>
            &lt;OrgUnit />
        &lt;/Publisher>
    &lt;/Publishers>
    &lt;License>https://creativecommons.org/licenses/by/4.0/&lt;/License>
    &lt;Keyword>machine learning&lt;/Keyword>
    &lt;Keyword>security and privacy&lt;/Keyword>
   	&lt;Abstract>Machine learning methods have become a commodity in the toolkits of both researchers and practitioners. For performance and privacy reasons, new applications often rely on third-party code or pretrained models, train on crowd-sourced data, and sometimes move learning to users’ devices. This introduces vulnerabilities such as backdoors, i.e., unrelated tasks that the model may unintentionally learn when an adversary controls parts of the training data or pipeline. In this thesis, we identify new threats to ML models and propose approaches that balance security, accuracy, and privacy without disruptive changes to the existing training infrastructures.&lt;/Abstract>
	&lt;Access xmlns="http://purl.org/coar/access_right" 
    >
    &lt;/Access>
&lt;/Publication>
</dim:field>
</dim:dim>
</metadata></record></GetRecord></OAI-PMH>