2026-09-23T01:37:36Z https://www.ideals.illinois.edu/oai-pmh

oai:www.ideals.illinois.edu:2142/130042 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 'U of I Access', the embargo will last until 2027-08-01 The student, Chulin Xie, accepted the attached license on 2025-07-14 at 13:43. The student, Chulin Xie, submitted this Dissertation for approval on 2025-07-14 at 14:08. This Dissertation was approved for publication on 2025-07-17 at 15:18. DSpace SAF Submission Ingestion Package generated from Vireo submission #22551 on 2025-10-21 at 10:06:04 Improving trustworthiness in machine learning Xie, Chulin 2025-07-17 Li, Bo Li, Bo Forsyth, David Ji, Heng Zhao, Han Koyejo, Sanmi Zhang, Ce Machine Learning Trustworthy eng As machine learning (ML) systems continue to scale in size and capability, concerns about their trustworthiness are increasing. This thesis addresses these challenges in the context of state-of-the-art ML systems, with a particular focus on foundation models and distributed learning. The work is organized around three interconnected pillars of trustworthy ML: privacy, robustness, and generalization. We begin by outlining the key challenges to the reliability of modern ML systems. Building on this foundation, we propose a set of methods aimed at improving the trustworthiness of ML deployment. These include methods for mitigating privacy risks through differentially private mechanisms, enhancing robustness against adversarial perturbations via certifiably robust algorithms, and identifying and addressing generalization failures. By analyzing risks and introducing mitigation strategies with theoretical guarantees, this thesis contributes scalable approaches for improving the reliability of ML systems. 2025-08 Text https://hdl.handle.net/2142/130042 Copyright 2025 Chulin Xie Siebel School Comp & Data Sci Computer Science University of Illinois Urbana-Champaign Ph.D. Dissertation