vCNN: Verifiable Convolutional Neural Network Based on zk-SNARKs

IF 7 2区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

IEEE Transactions on Dependable and Secure Computing Pub Date : 2024-07-01 DOI:10.1109/TDSC.2023.3348760

Seunghwan Lee, Hankyung Ko, Jihye Kim, Hyunok Oh

{"title":"vCNN: Verifiable Convolutional Neural Network Based on zk-SNARKs","authors":"Seunghwan Lee, Hankyung Ko, Jihye Kim, Hyunok Oh","doi":"10.1109/TDSC.2023.3348760","DOIUrl":null,"url":null,"abstract":"It is becoming important for the client to be able to check whether the AI inference services have been correctly calculated. Since the weight values in a CNN model are assets of service providers, the client should be able to check the correctness of the result without them. The Zero-knowledge Succinct Non-interactive Argument of Knowledge (zk-SNARK) allows verifying the result without input and weight values. However, the proving time in zk-SNARK is too slow to be applied to real AI applications. This article proposes a new efficient verifiable convolutional neural network (vCNN) framework that greatly accelerates the proving performance. We introduce a new efficient relation representation for convolution equations, reducing the proving complexity of convolution from O(ln) to O(l+n) compared to existing zero-knowledge succinct non-interactive argument of knowledge (zk-SNARK) approaches, where l and n denote the size of the kernel and the data in CNNs. Experimental results show that the proposed vCNN improves proving performance by 20-fold for a simple MNIST and 18,000-fold for VGG16. The security of the proposed scheme is formally proven.","PeriodicalId":13047,"journal":{"name":"IEEE Transactions on Dependable and Secure Computing","volume":null,"pages":null},"PeriodicalIF":7.0000,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"34","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Transactions on Dependable and Secure Computing","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1109/TDSC.2023.3348760","RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, HARDWARE & ARCHITECTURE","Score":null,"Total":0}

引用次数: 34

Abstract

It is becoming important for the client to be able to check whether the AI inference services have been correctly calculated. Since the weight values in a CNN model are assets of service providers, the client should be able to check the correctness of the result without them. The Zero-knowledge Succinct Non-interactive Argument of Knowledge (zk-SNARK) allows verifying the result without input and weight values. However, the proving time in zk-SNARK is too slow to be applied to real AI applications. This article proposes a new efficient verifiable convolutional neural network (vCNN) framework that greatly accelerates the proving performance. We introduce a new efficient relation representation for convolution equations, reducing the proving complexity of convolution from O(ln) to O(l+n) compared to existing zero-knowledge succinct non-interactive argument of knowledge (zk-SNARK) approaches, where l and n denote the size of the kernel and the data in CNNs. Experimental results show that the proposed vCNN improves proving performance by 20-fold for a simple MNIST and 18,000-fold for VGG16. The security of the proposed scheme is formally proven.

查看原文本刊更多论文

vCNN：基于 zk-SNARKs 的可验证卷积神经网络

对于客户来说，检查人工智能推理服务的计算是否正确变得越来越重要。由于 CNN 模型中的权重值是服务提供商的资产，因此客户应该能够在没有权重值的情况下检查结果的正确性。零知识简洁非交互式知识论证（zk-SNARK）允许在没有输入和权重值的情况下验证结果。然而，zk-SNARK 的证明时间太慢，无法应用于实际的人工智能应用。本文提出了一种新的高效可验证卷积神经网络（vCNN）框架，大大加快了证明性能。与现有的零知识简洁非交互式知识论证（zk-SNARK）方法相比，我们为卷积方程引入了一种新的高效关系表示法，将卷积的证明复杂度从 O(ln) 降低到 O(l+n)，其中 l 和 n 分别表示 CNN 中内核和数据的大小。实验结果表明，对于简单的 MNIST，所提出的 vCNN 将证明性能提高了 20 倍，对于 VGG16 则提高了 18000 倍。拟议方案的安全性已得到正式证明。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

IEEE Transactions on Dependable and Secure Computing 工程技术-计算机：软件工程

CiteScore

11.20

自引率

5.50%

发文量

354

审稿时长

9 months

期刊介绍： The "IEEE Transactions on Dependable and Secure Computing (TDSC)" is a prestigious journal that publishes high-quality, peer-reviewed research in the field of computer science, specifically targeting the development of dependable and secure computing systems and networks. This journal is dedicated to exploring the fundamental principles, methodologies, and mechanisms that enable the design, modeling, and evaluation of systems that meet the required levels of reliability, security, and performance. The scope of TDSC includes research on measurement, modeling, and simulation techniques that contribute to the understanding and improvement of system performance under various constraints. It also covers the foundations necessary for the joint evaluation, verification, and design of systems that balance performance, security, and dependability. By publishing archival research results, TDSC aims to provide a valuable resource for researchers, engineers, and practitioners working in the areas of cybersecurity, fault tolerance, and system reliability. The journal's focus on cutting-edge research ensures that it remains at the forefront of advancements in the field, promoting the development of technologies that are critical for the functioning of modern, complex systems.