Back to search

Virginia Tech

Understanding Machine Learning Models through a Data-Centric Lens

Abstract

dc:description.abstract

Foundation models acquire their capabilities by training on internet-scale corpora that are too large to fully inspect, filter, or audit. As a result, problematic data --- copyrighted material, personal records, and sensitive attributes --- can readily enter training and create privacy risks. At the same time, training data also shapes what a deployed model can do. This dissertation studies training data through these two perspectives, taking a data-centric view of foundation models: both the privacy risks and the capability levers come from the same training data. Part~I studies two privacy risks that training data can create. First, we develop a practical membership inference attack against large-scale multi-modal models under realistic constraints that preclude shadow training or access to the target training pipeline. Second, we identify a sustained spike in token-level prediction entropy as a precursor to memorized text emission and develop Confusion-Inducing Attacks, a principled extraction framework that systematically triggers this signal without privileged access to the training data. Part~II studies how training data shapes model capability and what model developers can do about it, through four practical levers: trace, remove, audit, and repair. We introduce the Mirrored Influence Hypothesis, which reformulates influence estimation around forward-pass-heavy computation and enables scalable data attribution at foundation-model scale. We then develop an unlearning framework based on the restricted gradient that removes targeted influence from text-to-image diffusion models while preserving text-image alignment on the remainder. Because removal can quietly damage benign capabilities that static benchmarks fail to reveal, we develop an adaptive probing framework that exposes knowledge holes --- unintended capability losses that emerge after unlearning. Finally, we develop Diagnosis-Driven Synthesis (DDS), which converts trace-level diagnoses of model failures into targeted training data and uses a diagnostic crossover operator to repair interacting weaknesses. Together, these four levers let model developers understand, audit, control, and improve foundation models through their training data.

Degree

thesis:*
Name thesis:degree_name
Doctor of Philosophy
Level thesis:degree_level
doctoral
Discipline thesis:degree_discipline
Computer Engineering
Department dc:contributor.department
Electrical and Computer Engineering
Grantor dc:publisher
Virginia Tech
Year dc:date.issued
2026

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Ko, Myeongseob
Chair dc:contributor.committeechair
  • Jia, Ruoxi
Committee members dc:contributor.committeemember
  • Williams, Ryan K.
  • Zeng, Haibo
  • Xiong, Wenjie
  • Cho, Jin-Hee

Subjects

dc:subject × 6

Rights

dc:rights
Statement dc:rights
  • In Copyright
Language dc:language.iso
en

Identifiers

dc:identifier.*
Dc Identifier Other
vt_gsexam:47100

Chain of custody

source
Harvested from
Virginia Tech
Base URL
vtechworks.lib.vt.edu/oai/request
Last updated
2026-11-18
Source record
OAI-PMH GetRecord
citation

Ko, Myeongseob. Understanding Machine Learning Models through a Data-Centric Lens. doctoral thesis, Virginia Tech, 2026. https://hdl.handle.net/10919/143302