2026-09-22T00:43:34Z https://www.ideals.illinois.edu/oai-pmh

oai:www.ideals.illinois.edu:2142/130183 2026-02-10 col_2142_5131 col_2142_10761 com_2142_5130 com_2142_10755 com_2142_234

application/pdf en text 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 Towards similarity learning in security applications Hao, Qingying 2025-07-15 Wang, Gang Wang, Gang Gunter, Carl Li, Bo Chandrasekaran, Varun Conti, Mauro Security Machine Learning Similarity Learning eng 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. 2025-08 Text https://hdl.handle.net/2142/130183 Copyright 2025 Qingying Hao Siebel School Comp & Data Sci Computer Science University of Illinois Urbana-Champaign Ph.D. Dissertation