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

2026-01-22

AI Summary

This work addresses the critical challenge of verifying the legitimacy and trustworthiness of outputs from financial large language models while simultaneously safeguarding model weights, training data copyrights, and user privacy. To this end, it introduces zkFinGPT—the first framework to integrate zero-knowledge proofs (ZKPs) into financial generative pre-trained models—leveraging the LLaMA3-8B architecture alongside cryptographic commitment schemes and protocols. The proposed approach enables verifiable inference without revealing any sensitive information. Experimental results demonstrate that on LLaMA3-8B, generating a 7.97 MB commitment takes 531 seconds, proof generation requires 620 seconds, and verification completes in merely 2.36 seconds. Although the overall computational overhead remains substantial, the method establishes a novel paradigm for trustworthy, privacy-preserving verification in high-value financial applications.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models
• Computer Vision: Large Vision Models

Application Category

• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Security and Privacy: Data transparency and provenance

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.

Problem

• FinGPT
• zero-knowledge proofs
• model verification
• intellectual property
• data privacy

Innovation

• Zero-Knowledge Proofs
• Financial Generative Pre-trained Transformers
• Model Verification
• Privacy-Preserving AI
• zkFinGPT