Private, Verifiable, and Auditable AI Systems
Name
south-tsouth-PhD-MAS-2025-thesis.pdf
Description
Thesis PDF
Size
4.26 MB
Format
Adobe PDF
Checksum (MD5)
86ce34d09569001fedfaed89532e6477
Author(s)
South, Tobin
Advisor(s)
Pentland, Alex 'Sandy'
Date Issued
May 2025
Publisher
Massachusetts Institute of Technology
Abstract
The growing societal reliance on artificial intelligence necessitates robust frameworks for ensuring its security, accountability, and trustworthiness. This thesis addresses the complex interplay between privacy, verifiability, and auditability in modern AI, particularly in foundation models. It argues that technical solutions that integrate these elements are critical for responsible AI innovation. Drawing from international policy contributions and technical research to identify key risks in the AI pipeline, this work introduces novel technical solutions for critical privacy and verifiability challenges. Specifically, the research introduces techniques for enabling verifiable and auditable claims about AI systems using zero-knowledge cryptography; utilizing secure multi-party computation and trusted execution environments for auditable, confidential deployment of large language models and information retrieval; and implementing enhanced delegation mechanisms, credentialing systems, and access controls to secure interactions with autonomous and multi-agent AI systems. Synthesizing these technical advancements, this dissertation presents a cohesive perspective on balancing privacy, verifiability, and auditability in foundation model-based AI systems, offering practical blueprints for system designers and informing policy discussions on AI safety and governance.
MIT Department
Program in Media Arts and Sciences (Massachusetts Institute of Technology)
Terms of Use
Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)
Copyright retained by author(s)
Persistent DSpace Link
