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.

翻译：具备多模态能力的金融生成式预训练Transformer（FinGPT）正日益广泛地应用于各类金融场景。然而，由于模型权重的知识产权、训练语料及基准问题的版权归属问题，验证GPT模型权重的合法性及模型输出的可信度已成为一项紧迫挑战。本文提出一种创新的zkFinGPT方案，将零知识证明应用于高价值金融场景，在保护数据隐私的同时实现可验证性。我们阐述了zkFinGPT在三个金融应用场景中的实施方案。基于两个现有工具包的实验表明，zkFinGPT会引入显著的计算开销，阻碍其实际落地。例如，对于LLama3-8B模型，生成承诺文件需$7.97$MB存储空间及$531$秒时间，证明过程耗时$620$秒，验证过程需$2.36$秒。