SecBNN: Efficient Secure Inference on Binary Neural Networks

IF 6.3 1区 计算机科学 Q1 COMPUTER SCIENCE, THEORY & METHODS
Hanxiao Chen;Hongwei Li;Meng Hao;Jia Hu;Guowen Xu;Xilin Zhang;Tianwei Zhang
{"title":"SecBNN: Efficient Secure Inference on Binary Neural Networks","authors":"Hanxiao Chen;Hongwei Li;Meng Hao;Jia Hu;Guowen Xu;Xilin Zhang;Tianwei Zhang","doi":"10.1109/TIFS.2024.3484936","DOIUrl":null,"url":null,"abstract":"This work studies secure inference on Binary Neural Networks (BNNs), which have binary weights and activations as a desirable feature. Although previous works have developed secure methodologies for BNNs, they still have performance limitations and significant gaps in efficiency when applied in practice. We present SecBNN, an efficient secure two-party inference framework on BNNs. SecBNN exploits appropriate underlying primitives and contributes efficient protocols for the non-linear and linear layers of BNNs. Specifically, for non-linear layers, we introduce a secure sign protocol with an innovative adder logic and customized evaluation algorithms. For linear layers, we propose a new binary matrix multiplication protocol, where a divide-and-conquer strategy is provided to recursively break down the matrix multiplication problem into multiple sub-problems. Building on top of these efficient ingredients, we implement and evaluate SecBNN over two real-world datasets and various model architectures under LAN and WAN. Experimental results show that SecBNN substantially improves the communication and computation performance of existing secure BNN inference works by up to \n<inline-formula> <tex-math>$29 \\times $ </tex-math></inline-formula>\n and \n<inline-formula> <tex-math>$14 \\times $ </tex-math></inline-formula>\n, respectively.","PeriodicalId":13492,"journal":{"name":"IEEE Transactions on Information Forensics and Security","volume":null,"pages":null},"PeriodicalIF":6.3000,"publicationDate":"2024-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Transactions on Information Forensics and Security","FirstCategoryId":"94","ListUrlMain":"https://ieeexplore.ieee.org/document/10750887/","RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, THEORY & METHODS","Score":null,"Total":0}
引用次数: 0

Abstract

This work studies secure inference on Binary Neural Networks (BNNs), which have binary weights and activations as a desirable feature. Although previous works have developed secure methodologies for BNNs, they still have performance limitations and significant gaps in efficiency when applied in practice. We present SecBNN, an efficient secure two-party inference framework on BNNs. SecBNN exploits appropriate underlying primitives and contributes efficient protocols for the non-linear and linear layers of BNNs. Specifically, for non-linear layers, we introduce a secure sign protocol with an innovative adder logic and customized evaluation algorithms. For linear layers, we propose a new binary matrix multiplication protocol, where a divide-and-conquer strategy is provided to recursively break down the matrix multiplication problem into multiple sub-problems. Building on top of these efficient ingredients, we implement and evaluate SecBNN over two real-world datasets and various model architectures under LAN and WAN. Experimental results show that SecBNN substantially improves the communication and computation performance of existing secure BNN inference works by up to $29 \times $ and $14 \times $ , respectively.
SecBNN:二元神经网络的高效安全推理
这项工作研究的是二元神经网络(BNN)的安全推理,二元神经网络具有二元权值和激活度这一理想特征。虽然之前的研究已经开发出了针对二元神经网络的安全方法,但在实际应用中,这些方法仍然存在性能限制和效率上的巨大差距。我们提出了 SecBNN,这是一种高效安全的 BNN 两方推理框架。SecBNN 利用适当的底层基元,为 BNN 的非线性层和线性层提供了高效协议。具体来说,对于非线性层,我们采用创新的加法器逻辑和定制的评估算法引入了一个安全符号协议。对于线性层,我们提出了一种新的二进制矩阵乘法协议,其中提供了一种 "分而治之 "策略,可递归地将矩阵乘法问题分解为多个子问题。在这些高效要素的基础上,我们在局域网和广域网的两个真实数据集和各种模型架构上实现并评估了 SecBNN。实验结果表明,SecBNN大幅提高了现有安全BNN推理的通信和计算性能,分别提高了29倍和14倍。
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 Information Forensics and Security
IEEE Transactions on Information Forensics and Security 工程技术-工程:电子与电气
CiteScore
14.40
自引率
7.40%
发文量
234
审稿时长
6.5 months
期刊介绍: The IEEE Transactions on Information Forensics and Security covers the sciences, technologies, and applications relating to information forensics, information security, biometrics, surveillance and systems applications that incorporate these features
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信