A Framework for Cryptographic Verifiability of End-to-End AI Pipelines
This addresses the need for auditability and regulatory compliance in AI deployment across industries, though it is incremental as it builds on existing cryptographic approaches.
The paper tackles the problem of ensuring transparency and trust in AI systems by proposing a framework for cryptographic verifiability across the entire AI pipeline, from data sourcing to inference, to combat misinformation through verifiable provenance and correctness.
The increasing integration of Artificial Intelligence across multiple industry sectors necessitates robust mechanisms for ensuring transparency, trust, and auditability of its development and deployment. This topic is particularly important in light of recent calls in various jurisdictions to introduce regulation and legislation on AI safety. In this paper, we propose a framework for complete verifiable AI pipelines, identifying key components and analyzing existing cryptographic approaches that contribute to verifiability across different stages of the AI lifecycle, from data sourcing to training, inference, and unlearning. This framework could be used to combat misinformation by providing cryptographic proofs alongside AI-generated assets to allow downstream verification of their provenance and correctness. Our findings underscore the importance of ongoing research to develop cryptographic tools that are not only efficient for isolated AI processes, but that are efficiently `linkable' across different processes within the AI pipeline, to support the development of end-to-end verifiable AI technologies.