{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/130183"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/130183","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Towards similarity learning in security applications","abstract":"Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2027-08-01","abstract_html":"Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2027-08-01","abstract_has_math":false,"creators":["Hao, Qingying"],"institution":"University of Illinois Urbana-Champaign","degree_name":"Ph.D.","degree_level":"Dissertation","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Wang, Gang","Gunter, Carl","Li, Bo","Chandrasekaran, Varun","Conti, Mauro"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025-07-15","date_published":"2025-07-15","updated_at":"2026-07-22T22:25:06Z","subjects":["Security","Machine Learning","Similarity Learning"],"languages":["en","eng"],"rights":["Copyright 2025 Qingying Hao"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/2142/130183","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Wang, Gang","Gunter, Carl","Li, Bo","Chandrasekaran, Varun","Conti, Mauro"]},{"key":"dc:creator","label":"Author","values":["Hao, Qingying"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2025-07-15","2025-08"]},{"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 Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Security","Machine Learning","Similarity Learning"]}]},{"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 2025 Qingying Hao"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://hdl.handle.net/2142/130183"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2027-08-01","The student, Qingying Hao, accepted the attached license on 2025-07-14 at 16:47.","The student, Qingying Hao, submitted this Dissertation for approval on 2025-07-14 at 22:25.","This Dissertation was approved for publication on 2025-07-15 at 12:53.","DSpace SAF Submission Ingestion Package generated from Vireo submission #22558 on 2025-10-25 at 15:53:55","In today’s world, large amounts of data remain unlabeled, posing a major challenge, especially in security applications, where acquiring high-quality labels is costly and difficult. Without accurate labels, it is hard to train reliable machine learning (ML) models, which limits their effectiveness in real-world scenarios. Similarity learning provides a promising direction by capturing relationships within the data without requiring explicit labels. Instead, it learns from reference pairs by measuring similarity through distance. While simple distance metrics can be used , similarity learning is often combined with deep learning to learn robust feature representations for comparison using predefined or learned similarity measures. How reliable is similarity learning in real-world security applications, particularly when exposed to adversarial threats? Under what conditions can it enhance model generalization and detection performance? This dissertation evaluates the robustness of similarity-learning applications under a realistic threat model by applying adversarial attacks end-to-end, and shows how similarity learning can improve out-of-distribution (OOD) generalization in graph-structured data. Specifically, Chapter 3 presents adversarial attacks targeting perceptual hashing-based reverse image search engines, which use Hamming distance as the similarity metric. By developing advanced attacks and evaluating them end-to-end on real-world systems, our framework successfully subverts several major reverse image search engines. In Chapter 4, we present attacks on vision-based phishing detectors trained using similarity learning. Our framework generates adversarial logos that preserve original brand semantics while bypassing state-of-the-art visual phishing website detectors. Chapter 5 explores how similarity learning, specifically graph contrastive learning (GCL), can complement supervised learning to improve out-of-distribution generalization in graph neural networks (GNNs) under natural distribution shifts. In summary, these studies show that similarity learning-based applications are vulnerable to adversarial attacks, highlighting the need for stronger defenses under realistic end-to-end threat models. At the same time, similarity learning can complement supervised methods by providing diverse feature representations and decision signals, making it valuable for improving out-of-distribution detection under natural distribution shifts."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Towards similarity learning in security applications"]}]}],"canonical_facts":{"dc:contributor":["Wang, Gang","Gunter, Carl","Li, Bo","Chandrasekaran, Varun","Conti, Mauro"],"dc:creator":["Hao, Qingying"],"dc:date":["2025-07-15","2025-08"],"dc:description":["Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2027-08-01","The student, Qingying Hao, accepted the attached license on 2025-07-14 at 16:47.","The student, Qingying Hao, submitted this Dissertation for approval on 2025-07-14 at 22:25.","This Dissertation was approved for publication on 2025-07-15 at 12:53.","DSpace SAF Submission Ingestion Package generated from Vireo submission #22558 on 2025-10-25 at 15:53:55","In today’s world, large amounts of data remain unlabeled, posing a major challenge, especially in security applications, where acquiring high-quality labels is costly and difficult. Without accurate labels, it is hard to train reliable machine learning (ML) models, which limits their effectiveness in real-world scenarios. Similarity learning provides a promising direction by capturing relationships within the data without requiring explicit labels. Instead, it learns from reference pairs by measuring similarity through distance. While simple distance metrics can be used , similarity learning is often combined with deep learning to learn robust feature representations for comparison using predefined or learned similarity measures. How reliable is similarity learning in real-world security applications, particularly when exposed to adversarial threats? Under what conditions can it enhance model generalization and detection performance? This dissertation evaluates the robustness of similarity-learning applications under a realistic threat model by applying adversarial attacks end-to-end, and shows how similarity learning can improve out-of-distribution (OOD) generalization in graph-structured data. Specifically, Chapter 3 presents adversarial attacks targeting perceptual hashing-based reverse image search engines, which use Hamming distance as the similarity metric. By developing advanced attacks and evaluating them end-to-end on real-world systems, our framework successfully subverts several major reverse image search engines. In Chapter 4, we present attacks on vision-based phishing detectors trained using similarity learning. Our framework generates adversarial logos that preserve original brand semantics while bypassing state-of-the-art visual phishing website detectors. Chapter 5 explores how similarity learning, specifically graph contrastive learning (GCL), can complement supervised learning to improve out-of-distribution generalization in graph neural networks (GNNs) under natural distribution shifts. In summary, these studies show that similarity learning-based applications are vulnerable to adversarial attacks, highlighting the need for stronger defenses under realistic end-to-end threat models. At the same time, similarity learning can complement supervised methods by providing diverse feature representations and decision signals, making it valuable for improving out-of-distribution detection under natural distribution shifts."],"dc:format":["application/pdf"],"dc:identifier":["https://hdl.handle.net/2142/130183"],"dc:language":["en","eng"],"dc:rights":["Copyright 2025 Qingying Hao"],"dc:subject":["Security","Machine Learning","Similarity Learning"],"dc:title":["Towards similarity learning in security applications"],"dc:type":["text"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Dissertation"],"thesis:degree_name":["Ph.D."],"thesis:institution_name":["University of Illinois Urbana-Champaign"]},"updated_at":"2026-07-22T22:25:06Z"}