# Private, Verifiable, and Auditable AI Systems

## TL;DR

This paper presents novel technical solutions to enhance privacy, verifiability, and auditability in AI systems, especially foundation models, using cryptography, secure computation, and access controls to promote responsible AI development.

## Contribution

It introduces integrated methods combining cryptography, secure computation, and access controls to address privacy and verifiability challenges in modern AI systems.

## Key findings

- Developed zero-knowledge proof techniques for verifiable AI claims.
- Utilized secure multi-party computation for confidential AI deployment.
- Proposed enhanced access controls for autonomous AI systems.

## 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.