Privacy-Preserving Convolutional Neural Network Classification Scheme With Multiple Keys

计算机科学 同态加密 卷积神经网络 激活函数 密码系统 信息隐私 加密 功能加密 公钥密码术 理论计算机科学 密文 人工智能 数据挖掘 计算机安全 人工神经网络
作者
Baocang Wang,Yange Chen,Furong Li,Jian Song,Rongxing Lu,Pu Duan,Zhihong Tian
出处
期刊:IEEE Transactions on Services Computing [Institute of Electrical and Electronics Engineers]
卷期号:17 (1): 322-335 被引量:2
标识
DOI:10.1109/tsc.2023.3349298
摘要

Convolutional Neural Networks (CNNs) possess extensive applicability across diverse domains, particularly in the realm of image recognition. In light of the advent of machine learning as a service, the utilization of a well-trained CNN model by servers to execute image classification based on user queries has become a significant service, catering to a wide array of applications. Nevertheless, this convenience is accompanied by the inherent risk of data privacy and model privacy disclosure, which can have severe ramifications, particularly in the context of specialized scenarios like medical images and location images. Hence, how to perform classification for CNN with privacy protection emerges as a crucial research concern. Furthermore, the nonlinearity of CNN's activation function renders it unsuitable for homomorphic cryptosystems. In order to address these challenges, we put forth a privacy-preserving CNN classification scheme employing a distributed two trapdoors public-key cryptosystem (DT-PKC). Initially, we introduce a security protocol toolkit encompassing protocols for secure multiplication, secure activation function computing, and average pooling. In addition, we propose a novel continuous and derivative Tanhplus function as an approximation of the Relu function, aiming to enhance the accuracy of classification results. The secure activation function computing protocol utilizes the aforementioned Tanhplus function in conjunction with the proposed homogenization algorithm to compute the activation function. This protocol guarantees more precise and accurate output in the activation function calculation of CNN when operating under ciphertext. Furthermore, the adoption of the DT-PKC cryptosystem not only ensures privacy protection for CNN classification but also provides support for lightweight users and multiple keys. Finally, security analysis and performance evaluations demonstrate that the proposed scheme is secure, practicable, and efficient with high accuracy.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
sammy完成签到 ,获得积分10
刚刚
fhc发布了新的文献求助30
1秒前
桐桐的应助被山海不远采纳,获得30
1秒前
打打的应助被霁月采纳,获得10
1秒前
tanglu完成签到,获得积分10
1秒前
h31318927完成签到,获得积分10
1秒前
1秒前
fifi完成签到,获得积分10
2秒前
2秒前
李李完成签到,获得积分10
2秒前
无花果的应助被诚心的访蕊采纳,获得10
2秒前
2秒前
2秒前
西瓜翠衣完成签到,获得积分10
3秒前
3秒前
归亦完成签到,获得积分10
3秒前
温婉完成签到,获得积分10
3秒前
4秒前
鉴湖完成签到,获得积分10
4秒前
fzkls发布了新的文献求助10
4秒前
852的应助被之之采纳,获得10
4秒前
轩辕沛柔完成签到,获得积分10
5秒前
甜馨完成签到,获得积分10
6秒前
可耐的盼秋完成签到 ,获得积分10
6秒前
PYR发布了新的文献求助10
6秒前
6秒前
正直西牛完成签到,获得积分20
6秒前
爆米花的应助被Puffkten采纳,获得10
7秒前
7秒前
lwk发布了新的文献求助10
7秒前
自由的骁完成签到,获得积分10
7秒前
欢欢完成签到,获得积分10
7秒前
8秒前
前行的灿发布了新的文献求助10
8秒前
halo完成签到,获得积分10
8秒前
Mmary完成签到 ,获得积分10
8秒前
搜集达人的应助被HouKk采纳,获得10
8秒前
容易记关注了科研通微信公众号
9秒前
万能图书馆的应助被星空采纳,获得10
9秒前
李源高完成签到,获得积分10
9秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
John McDowells Bildungstheorie 800
Social Psychology in the Real World 600
八旗制度の研究 600
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8180531
求助须知:如何正确求助?哪些是违规求助? 9570507
关于积分的说明 21812974
捐赠科研通 7776619
什么是DOI,文献DOI怎么找? 3433286
关于科研通互助平台的介绍 2557539
邀请新用户注册赠送积分活动 2479185