无需暴露模型参数即可验证AI推理正确性，保障隐私与可信。
Zero-Knowledge Proof Based Verifiable Inference of Models
- 用递归零知识证明框架验证模型推理过程
- 实现常数大小证明，支持线性与非线性层
- 适用于保护知识产权的AI验证场景
近年来，人工智能尤其是深度学习在各领域广泛应用，但一个根本挑战是：当模型所有者无法或不愿公开模型参数时，如何验证其推理结果的正确性？这些参数承载巨大训练成本和重要知识产权，透明验证困难。本文提出一种基于零知识证明的框架，可在不暴露模型内部参数的前提下验证深度学习推理过程。该框架采用递归组合的零知识证明，无需可信设置，支持矩阵乘法、归一化、softmax 和 SiLU 等线性与非线性神经网络层。通过 Fiat-Shamir 变换，获得常数大小的非交互式知识论证（zkSNARK）。为验证实用性，我们成功将 DeepSeek 模型转换为全可 SNARK 验证版本 ZK-DeepSeek，实验表明该框架在真实 AI 验证任务中兼具高效性与灵活性。
原文摘要 · Abstract (English)
Recent advances in artificial intelligence (AI), particularly deep learning, have led to widespread adoption across various applications. Yet, a fundamental challenge persists: how can we verify the correctness of AI model inference when model owners cannot (or will not) reveal their parameters? These parameters represent enormous training costs and valuable intellectual property, making transparent verification difficult. In this paper, we introduce a zero-knowledge framework capable of verifying deep learning inference without exposing model internal parameters. Built on recursively composed zero-knowledge proofs and requiring no trusted setup, our framework supports both linear and nonlinear neural network layers, including matrix multiplication, normalization, softmax, and SiLU. Leveraging the Fiat-Shamir heuristic, we obtain a succinct non-interactive argument of knowledge (zkSNARK) with constant-size proofs. To demonstrate the practicality of our approach, we translate the DeepSeek model into a fully SNARK-verifiable version named ZK-DeepSeek and show experimentally that our framework delivers both efficiency and flexibility in real-world AI verification workloads.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。