{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/121313"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/121313","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Enhancing the robustness of machine learning models","abstract":"Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2025-08-01","abstract_html":"Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2025-08-01","abstract_has_math":false,"creators":["Xu, Xiaojun"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"Ph.D.","degree_level":"Dissertation","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Gunter, Carl A.","Li, Bo","Borisov, Nikita","Zhang, Ce"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2023,"date_issued":"2023-08","date_published":"2023-08","updated_at":"2026-07-22T22:24:57Z","subjects":["Machine Learning Robustness"],"languages":["en","eng"],"rights":["Copyright 2023 Xiaojun Xu"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/2142/121313","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Gunter, Carl A.","Li, Bo","Borisov, Nikita","Zhang, Ce"]},{"key":"dc:creator","label":"Author","values":["Xu, Xiaojun"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2023-08","2023-06-21"]},{"key":"dc:type","label":"Dc Type","values":["text"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Dissertation"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Ph.D."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Illinois at Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Machine Learning Robustness"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en","eng"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2023 Xiaojun Xu"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://hdl.handle.net/2142/121313"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2025-08-01","The student, Xiaojun Xu, accepted the attached license on 2023-06-20 at 21:41.","The student, Xiaojun Xu, submitted this Dissertation for approval on 2023-06-20 at 21:46.","This Dissertation was approved for publication on 2023-06-21 at 16:09.","DSpace SAF Submission Ingestion Package generated from Vireo submission #19440 on 2023-12-04 at 17:18:02","Machine learning models have recently shown surprisingly good performance in real-world tasks. Therefore, there are growing concerns about whether machine learning models can be robust against different potential threats. In this thesis, we will explore the robustness of machine learning models against adversarial threats in three scenarios that have received relatively less attention from the community. Firstly, we will investigate backdoor attacks, which involve perturbing both the training and evaluation stages. As a countermeasure to such a stealthy and dangerous attack, we present a countermeasure by achieving a binary classification task on neural networks to mitigate this type of threat. Secondly, we will examine the robustness of graph data. We demonstrate the potential threat for discrete edge space manipulation to deceive graph neural networks and make desired actions with stealthy perturbations. We also offer a countermeasure to detect the maliciously injected edges on graph data with an ensemble of multiple models. Finally, we will discuss how model architecture design can provide a robustness guarantee. We present two Lipschitz-constrained models, one for convolution networks and another for Transformer networks. We show that such Lipschitz-constrained models can achieve good certified model robustness. Our work enhances machine learning robustness against various adversarial threats with effective countermeasures."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Enhancing the robustness of machine learning models"]}]}],"canonical_facts":{"dc:contributor":["Gunter, Carl A.","Li, Bo","Borisov, Nikita","Zhang, Ce"],"dc:creator":["Xu, Xiaojun"],"dc:date":["2023-08","2023-06-21"],"dc:description":["Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2025-08-01","The student, Xiaojun Xu, accepted the attached license on 2023-06-20 at 21:41.","The student, Xiaojun Xu, submitted this Dissertation for approval on 2023-06-20 at 21:46.","This Dissertation was approved for publication on 2023-06-21 at 16:09.","DSpace SAF Submission Ingestion Package generated from Vireo submission #19440 on 2023-12-04 at 17:18:02","Machine learning models have recently shown surprisingly good performance in real-world tasks. Therefore, there are growing concerns about whether machine learning models can be robust against different potential threats. In this thesis, we will explore the robustness of machine learning models against adversarial threats in three scenarios that have received relatively less attention from the community. Firstly, we will investigate backdoor attacks, which involve perturbing both the training and evaluation stages. As a countermeasure to such a stealthy and dangerous attack, we present a countermeasure by achieving a binary classification task on neural networks to mitigate this type of threat. Secondly, we will examine the robustness of graph data. We demonstrate the potential threat for discrete edge space manipulation to deceive graph neural networks and make desired actions with stealthy perturbations. We also offer a countermeasure to detect the maliciously injected edges on graph data with an ensemble of multiple models. Finally, we will discuss how model architecture design can provide a robustness guarantee. We present two Lipschitz-constrained models, one for convolution networks and another for Transformer networks. We show that such Lipschitz-constrained models can achieve good certified model robustness. Our work enhances machine learning robustness against various adversarial threats with effective countermeasures."],"dc:format":["application/pdf"],"dc:identifier":["https://hdl.handle.net/2142/121313"],"dc:language":["en","eng"],"dc:rights":["Copyright 2023 Xiaojun Xu"],"dc:subject":["Machine Learning Robustness"],"dc:title":["Enhancing the robustness of machine learning models"],"dc:type":["text"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Dissertation"],"thesis:degree_name":["Ph.D."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:24:57Z"}