Content area

Abstract

Research over the last decade shows that machine learning (ML) models are vulnerable to adversarial manipulations. Particularly, input perturbations which are incomprehensible to humans, can force models to behave unexpectedly. However, existing research analyses these models in isolation, neglecting the broader system context typical of real-world deployments where an ML model is merely one component within a larger application. In two parts, this thesis investigates the security implications of this system-level perspective, exploring both the challenges and opportunities presented by the interplay between ML models and the surrounding environment. In the first half, we explore how to evaluate the security of ML systems. We highlight how existing methods fail in this setting, and provide new frameworks that can account for the components surrounding the ML model. We focus on techniques that can be integrated into existing evaluation methods, adapting them to be system-context aware. In the second half, we design robust ML systems. We provide systems where the non-ML components can compensate for the vulnerabilities of the ML model. This includes leveraging the surrounding software infrastructure and interaction protocols to create robust systems. Overall, this thesis takes a step towards a more systems approach to ML security.

Details

1010268
Title
Robustness of Multi-Component Machine Learning Systems
Number of pages
220
Publication year
2025
Degree date
2025
School code
0262
Source
DAI-A 86/11(E), Dissertation Abstracts International
ISBN
9798314883402
Committee member
Fernandes, Earlence; Chatterjee, Rahul
University/institution
The University of Wisconsin - Madison
Department
Computer Sciences
University location
United States -- Wisconsin
Degree
Ph.D.
Source type
Dissertation or Thesis
Language
English
Document type
Dissertation/Thesis
Dissertation/thesis number
32040552
ProQuest document ID
3203045631
Document URL
https://www.proquest.com/dissertations-theses/robustness-multi-component-machine-learning/docview/3203045631/se-2?accountid=208611
Copyright
Database copyright ProQuest LLC; ProQuest does not claim copyright in the individual underlying works.
Database
ProQuest One Academic