zkFinGPT: Zero-Knowledge Proofs for Financial Generative Pre-trained Transformers

TL;DR

This paper proposes zkFinGPT, a zero-knowledge proof scheme for financial GPT models that enables verification of model legitimacy and output credibility while preserving data privacy, though it incurs significant computational overhead.

Contribution

Introduction of zkFinGPT, a novel zero-knowledge proof framework tailored for financial GPT models to enhance trustworthiness and privacy in high-stakes financial applications.

Findings

zkFinGPT enables model verification and output credibility in financial AI.

The scheme introduces substantial computational overhead, affecting practical deployment.

Experiments demonstrate feasibility but highlight efficiency challenges.

Abstract

Financial Generative Pre-trained Transformers (FinGPT) with multimodal capabilities are now being increasingly adopted in various financial applications. However, due to the intellectual property of model weights and the copyright of training corpus and benchmarking questions, verifying the legitimacy of GPT's model weights and the credibility of model outputs is a pressing challenge. In this paper, we introduce a novel zkFinGPT scheme that applies zero-knowledge proofs (ZKPs) to high-value financial use cases, enabling verification while protecting data privacy. We describe how zkFinGPT will be applied to three financial use cases. Our experiments on two existing packages reveal that zkFinGPT introduces substantial computational overhead that hinders its real-world adoption. E.g., for LLama3-8B model, it generates a commitment file of $7.97$MB using $531$ seconds, and takes $620$ seconds to prove and $2.36$ seconds to verify.