SLFB-CNN: An interpretable neural network privacy protection framework

De Li, Yuhang Hu, Jinyan Wang
{"title":"SLFB-CNN: An interpretable neural network privacy protection framework","authors":"De Li, Yuhang Hu, Jinyan Wang","doi":"10.1109/CIS52066.2020.00070","DOIUrl":null,"url":null,"abstract":"The feedforward-designed convolutional neural network (FF-CNN) method was recently proposed by Kuo et al. It has strong interpretability and low training complexity. In this paper, we have proposed two improvements (1) We merge two algorithms Layer-wise Relevance Propagation (LRP) and FF-CNN to build an interpretable neural network framework called LFB-CNN. The back-propagation (BP) algorithm is used to train the fully connected layer of FF-CNN. Meanwhile, the LRP algorithm is used to decompose and calculate the correlation between the input and output of the fully connected layer, and further improve the model performance without reducing the interpretability. (2) We conducted a privacy analysis on the LFB-CNN framework. Once the parameters of the framework are disclosed, the privacy of the data provider will be leaked. Therefore, we use differential privacy to propose a secure LFB-CNN (SLFB-CNN) algorithm. At last, we verified the effectiveness of our proposed method on the MNIST, Fashion-MNIST and CIFAR-10 datasets.","PeriodicalId":106959,"journal":{"name":"2020 16th International Conference on Computational Intelligence and Security (CIS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2020-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2020 16th International Conference on Computational Intelligence and Security (CIS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CIS52066.2020.00070","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1

Abstract

The feedforward-designed convolutional neural network (FF-CNN) method was recently proposed by Kuo et al. It has strong interpretability and low training complexity. In this paper, we have proposed two improvements (1) We merge two algorithms Layer-wise Relevance Propagation (LRP) and FF-CNN to build an interpretable neural network framework called LFB-CNN. The back-propagation (BP) algorithm is used to train the fully connected layer of FF-CNN. Meanwhile, the LRP algorithm is used to decompose and calculate the correlation between the input and output of the fully connected layer, and further improve the model performance without reducing the interpretability. (2) We conducted a privacy analysis on the LFB-CNN framework. Once the parameters of the framework are disclosed, the privacy of the data provider will be leaked. Therefore, we use differential privacy to propose a secure LFB-CNN (SLFB-CNN) algorithm. At last, we verified the effectiveness of our proposed method on the MNIST, Fashion-MNIST and CIFAR-10 datasets.
SLFB-CNN:一个可解释的神经网络隐私保护框架
前馈设计卷积神经网络(FF-CNN)方法是最近由Kuo等人提出的。具有较强的可解释性和较低的训练复杂度。在本文中,我们提出了两个改进方案(1)我们将分层相关传播(Layer-wise Relevance Propagation, LRP)和FF-CNN两种算法合并,构建了一个可解释的神经网络框架LFB-CNN。采用反向传播(BP)算法训练FF-CNN的全连接层。同时,利用LRP算法对全连通层的输入与输出进行分解计算,在不降低可解释性的前提下进一步提高模型性能。(2)我们对LFB-CNN框架进行了隐私分析。一旦框架的参数被泄露,就会泄露数据提供者的隐私。因此,我们利用差分隐私提出了一种安全的LFB-CNN (SLFB-CNN)算法。最后,我们在MNIST、Fashion-MNIST和CIFAR-10数据集上验证了所提方法的有效性。
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
自引率
0.00%
发文量
0
×
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