Back to search

Michigan Technological University

ENHANCING PRIVACY WHILE REVEALING VULNERABILITIES: STRATEGIES FOR ADAPTATION, OPTIMIZATION, AND MODEL EXTRACTION

Abstract

dc:description.abstract

In the evolving landscape of machine learning and artificial intelligence, this dissertation presents a series of innovative contributions spanning several critical areas: embracing semi-supervised domain adaptation for secure knowledge transfer, enhancing the model performance of tiny models, and executing model stealing attacks via diversified prompts. The overarching goal is to enhance the performance, scalability, and security of AI models across various applications. The first research focus is on semi-supervised domain adaptation within federated learning frameworks. By leveraging semi-supervised learning techniques, this work addresses the challenge of adapting models trained on a source domain to perform effectively on a target domain with differing data distributions. This approach ensures the secure transfer of knowledge across domains without compromising data privacy. The second area of research explores the augmentation of heterogeneous models, particularly focusing on the integration of tiny and large models within federated learning environments. This innovative method demonstrates significant improvements in the efficiency and effectiveness of TinyML, enabling their deployment in resource-constrained environments. Lastly, the contribution is in the realm of secure model extraction and utilization. This research delves into the vulnerabilities of fine-tuned foundation models, proposing a novel attack method, termed "Siemese attack," that uses diversified prompts to steal the functionality of these models. The study highlights the importance of securing AI models against such threats while also exploring methods to safeguard the confidentiality of task-specific knowledge embedded within these models. Overall, the research presented in this dissertation advances the state-of-the-art in federated learning, tiny model performance, model stealing and secure AI practices. The findings have significant implications for the development of robust, efficient, and secure AI systems capable of addressing diverse and complex real-world challenges.

Degree

thesis:*
Name thesis:degree_name
Doctor of Philosophy in Computer Engineering (PhD)
Level thesis:degree_level
Open Access Dissertation
Discipline thesis:degree_discipline
Department of Electrical and Computer Engineering

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Das, Madhureeta
Committee members dc:contributor.committeemember
  • Lan Zhang
  • Hongyu An
  • Yu Cai
Contributors dc:contributor
  • Kaichen Yang

Subjects

dc:subject × 5

Rights

Identifiers

dc:identifier.*

Chain of custody

source
Harvested from
Michigan Technological University
Base URL
digitalcommons.mtu.edu/do/oai/
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Das, Madhureeta. ENHANCING PRIVACY WHILE REVEALING VULNERABILITIES: STRATEGIES FOR ADAPTATION, OPTIMIZATION, AND MODEL EXTRACTION. Open Access Dissertation thesis, https://doi.org/10.37099/mtu.dc.etdr/1860