Private, Verifiable, and Auditable AI Systems
By: Tobin South
Potential Business Impact:
Makes AI trustworthy and private for everyone.
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.
Similar Papers
Can AI be Auditable?
Computers and Society
Makes sure AI follows rules and is safe.
Can AI be Auditable?
Computers and Society
Makes AI systems fair and safe to use.
Can AI be Auditable?
Computers and Society
Makes sure AI works fairly and safely.