面向深度神经网络的安全计算协议设计方法

毕仁万; 陈前昕; 熊金波; 刘西蒙

doi:10.11959/j.issn.2096-109x.2020050

您当前的位置：

首页 >

文章列表页 >

面向深度神经网络的安全计算协议设计方法

学术论文 | 更新时间：2024-06-03

- 面向深度神经网络的安全计算协议设计方法
- Design method of secure computing protocol for deep neural network
- 网络与信息安全学报 2020年6卷第4期页码：130-139
- 作者机构：
  
  1. 福建师范大学数学与信息学院，福建福州 350117
  2. 福州大学数学与计算机科学学院，福建福州 350108
- 作者简介：
  
  [ "毕仁万（1996- ），男，湖南常德人，福建师范大学硕士生，主要研究方向为安全深度学习、安全多方计算" ]
  [ "陈前昕（1996- ），男，福建泉州人，福建师范大学硕士生，主要研究方向为安全深度学习、隐私保护技术" ]
  [ "熊金波（1981- ），男，湖南益阳人，博士，福建师范大学教授，主要研究方向为安全深度学习、移动群智感知、隐私保护技术" ]
  [ "刘西蒙（1988- ），男，陕西西安人，博士，福州大学教授，主要研究方向为云安全、应用密码学、大数据安全" ]
- 基金信息：
  
  国家自然科学基金资助项目;The National Natural Science Foundation of China(61872088);国家自然科学基金;The National Natural Science Foundation of China(U1804263);国家自然科学基金;The National Natural Science Foundation of China(61702105);国家自然科学基金资助项目;The National Natural Science Foundation of China(61872090);福建省自然科学基金资助项目;The Natural Science Foundation of Fujian Province(2019J01276);贵州省公共大数据重点实验室开放课题;The Guizhou Provincial Key Laboratory of Public Big Data Research Fund(2019BDKFJJ004)
- DOI：10.11959/j.issn.2096-109x.2020050
  中图分类号： TP393
- 网络首发：2020-08，
  
  纸质出版：2020-08-15
- 稿件说明：
移动端阅览
毕仁万, 陈前昕, 熊金波, 等. 面向深度神经网络的安全计算协议设计方法[J]. 网络与信息安全学报, 2020,6(4):130-139.

Renwan BI, Qianxin CHEN, Jinbo XIONG, et al. Design method of secure computing protocol for deep neural network[J]. Chinese Journal of Network and Information Security, 2020, 6(4): 130-139.
毕仁万, 陈前昕, 熊金波, 等. 面向深度神经网络的安全计算协议设计方法[J]. 网络与信息安全学报, 2020,6(4):130-139. DOI： 10.11959/j.issn.2096-109x.2020050.

Renwan BI, Qianxin CHEN, Jinbo XIONG, et al. Design method of secure computing protocol for deep neural network[J]. Chinese Journal of Network and Information Security, 2020, 6(4): 130-139. DOI： 10.11959/j.issn.2096-109x.2020050.

摘要

针对深度神经网络模型计算过程中存在的信息泄露问题，结合加性秘密共享方案，在两台非共谋的边缘服务器间设计安全高效的交互计算协议。考虑到非线性函数不能直接拆分，首先提出一组基本转换协议，实现加性副本和乘性副本的安全转换，经过少量调用，可以安全计算幂函数、比较、指数、对数、除法等底层函数。由于数据传递和计算特点，协议可以扩展至数组计算。理论分析证明了协议的正确性、高效性和安全性，实验结果表明，协议具有较小的误差，其计算和通信开销均优于现有设计方案。

Abstract

Aiming at the information leakage problem in the process of deep neural network model calculation

a series of secure and efficient interactive computing protocols were designed between two non-collusive edge servers in combination with the additive secret sharing scheme.Since the nonlinear function cannot be split directly

a set of basic conversion protocols were proposed to realize the secure conversion of additive and multiplicative shares.After a few invokes

the power

comparison

exponential

logarithm

division and other low-level functions can be calculated securely.Due to the characteristics of data transfer and computation

the proposed protocols can be extended to array computation.Theoretical analysis ensures the correctness

efficiency and security of these protocols.The experimental results show that the error of these protocols is negligible

and the computational costs and communication overhead are better than the existing schemes.

关键词

Keywords

references

ZHOU Y , TUZEL O . Voxelnet:end-to-end learning for point cloud based 3d object detection [C ] // The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) . 2018 : 4490 - 4499 .

REN S Q , HE K , GIRSHICK R , et al . Faster R-CNN:towards real-time object detection with region proposal networks [J ] . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2015 , 39 ( 6 ): 91 - 99 .

YANN L , BERNHARD B , JOHN S D , et al . Backpropagation applied to handwritten zip code recognition [J ] . Neural Computation , 1989 , 1 ( 4 ): 541 - 551 .

XIONG J B , BI R W , SZHAO M F , et al . Edge-assisted privacy-preserving raw data sharing framework for connected autonomous vehicles [J ] . IEEE Wireless Communications , 2020 , 27 ( 3 ): 24 - 30 .

HESAMIFARD E , TAKABI H , GHASEMI M . CryptoDL:deep neural networks over encrypted data [J ] . arXiv preprint arXiv:1711.05189 , 2017

MOHASSEL P , ZHANG Y P . SecureML:a system for scalable privacy-preserving machine learning [C ] // IEEE Symposium on Security and Privacy (S＆P) . 2017 : 19 - 38 .

YAO A C , . Protocols for secure computations [C ] // The 23rd Annual Symposium on Foundations of Computer Science (SFCS) . 1982 : 160 - 164 .

唐春明 , 魏伟明 . 基于安全两方计算的具有隐私性的回归算法 [J ] . 信息网络安全 , 2018 ( 10 ): 10 - 16 .

TANG C M , WEI W M . Regression algorithm with based on secure two-party computation [J ] . Information Network Security , 2018 ( 10 ): 10 - 16 .

RABIN M O . How to exchange secrets with oblivious transfer [J ] . IACR Cryptology ePrint Archive , 2005 :187.

刘新 , 李顺东 , 陈振华 . 基本初等函数的保密云计算服务协议 [J ] . 计算机科学 , 2015 , 42 ( 10 ): 159 - 163 .

LIU X , LI S D , CHEN Z H . Secure cloud computing service protocols of elementary functions [J ] . Computer Science , 2015 , 42 ( 10 ): 159 - 163 .

HUANG K , LIU X M , FU S J , et al . A lightweight privacy-preserving CNN feature extraction framework for mobile sensing [J ] . IEEE Transactions on Dependable and Secure Computing , 2019 :1.

MA Z , LIU Y , LIU X M , et al . Privacy-preserving outsourced speech recognition for smart IoT devices [J ] . IEEE Internet of Things Journal , 2019 , 6 ( 5 ): 8406 - 8420 .

LIU Y , MA Z , LIU X M , et al . Privacy-preserving object detection for medical images with Faster R-CNN [J ] . IEEE Transactions on Information Forensics and Security , 2019 :1.

VOLDER J E . The cordic trigonometric computing technique [J ] . IRE Transactions on Electronic Computers , 1959 , 8 ( 3 ): 330 - 334 .

ZHU Y W , HUANG L S , YANG W , et al . Three new approaches to privacy-preserving add to multiply protocol and its application [C ] // The 2nd International Workshop on Knowledge Discovery and Data Mining . 2009 : 554 - 558 .

李禾 , 王述洋 . 关于除法的安全双方计算协议 [J ] . 计算机工程与应用 , 2010 , 46 ( 6 ): 86 - 88 .

LI H , WANG S Y . Several secure two-party protocols of division [J ] . Computer Engineering and Applications , 2010 , 46 ( 6 ): 86 - 88 .

BOGDANOV D , LAUR S , WILLEMSON J . Sharemind:a framework for fast privacy-preserving computations [C ] // European Symposium on Research in Computer Security . 2008 : 192 - 206 .

BOGDANOV D , NIITSOO M , TOFT T , et al . High-performance secure multi-party computation for data mining applications [J ] . International Journal of Information Security , 2012 , 11 ( 6 ): 403 - 418 .

浏览量

619

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

车牌识别系统中基于特征不变量的对抗检测

载体独立的深度光照水印算法

基于深度神经网络的Android恶意软件检测方法