arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2502.18535cs.CRcs.AIcs.LG
收藏

基于零知识证明的可验证机器学习综述

A Survey of Zero-Knowledge Proof Based Verifiable Machine Learning

College of Electronics and Information Engineering, Shenzhen University(深圳大学电子与信息工程学院);School of Computer Science and Cyber Engineering, Guangzhou University(广州大学计算机科学与网络工程学院);School of Electronic and Information Engineering, South China University of Technology(华南理工大学电子与信息学院);State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications(北京邮电大学网络与交换技术国家重点实验室);School of Electronic and Optical Engineering, Nanjing University of Science and Technology(南京理工大学电子工程与光电技术学院)

Zhizhi Peng, Chonghe Zhao, Taotao Wang, Guofu Liao, Zibin Lin, Yifeng Liu, Bin Cao, Long Shi, Qing Yang, Shengli Zhang

AI总结:

本文综述了从2017年6月至2025年8月间发表的零知识机器学习研究,涵盖可验证训练、测试和推理三大核心任务,分析了实现瓶颈与改进技术,为可信隐私保护机器学习提供参考。

摘要:

机器学习正通过外包和云管道部署,提升了可访问性但引发计算完整性、数据隐私和模型保密性的担忧。零知识证明(ZKPs)为可验证机器学习提供了有力基础,允许一方证明训练、测试或推理结果由声称的计算产生而不泄露敏感数据或专有模型参数。尽管零知识机器学习(ZKML)快速进步,文献仍分散在不同密码学设置、机器学习任务和系统目标中。本文综述了ZKML研究,首先介绍ZKML背后的ZKP基本公式,将现有研究分为三大核心任务:可验证训练、可验证测试和可验证推理。随后综合代表性系统,比较其设计选择,分析主要实现瓶颈,包括有限电路表达能力、高证明成本和部署复杂性。此外,总结了提升通用性和效率的主要技术,回顾新兴商业努力,并讨论了有前途的未来方向。通过整合ZKML的设计空间,本文旨在为研究者和从业者提供结构化的参考,以推动可信和隐私保护的机器学习发展。

英文摘要:

Machine learning is increasingly deployed through outsourced and cloud-based pipelines, which improve accessibility but also raise concerns about computational integrity, data privacy, and model confidentiality. Zero-knowledge proofs (ZKPs) provide a compelling foundation for verifiable machine learning because they allow one party to certify that a training, testing, or inference result was produced by the claimed computation without revealing sensitive data or proprietary model parameters. Despite rapid progress in zero-knowledge machine learning (ZKML), the literature remains fragmented across different cryptographic settings, ML tasks, and system objectives. This survey presents a comprehensive review of ZKML research published from June 2017 to August 2025. We first introduce the basic ZKP formulations underlying ZKML and organize existing studies into three core tasks: verifiable training, verifiable testing, and verifiable inference. We then synthesize representative systems, compare their design choices, and analyze the main implementation bottlenecks, including limited circuit expressiveness, high proving cost, and deployment complexity. In addition, we summarize major techniques for improving generality and efficiency, review emerging commercial efforts, and discuss promising future directions. By consolidating the design space of ZKML, this survey aims to provide a structured reference for researchers and practitioners working on trustworthy and privacy-preserving machine learning.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑