Depthwise Separable Convolutional Neural Network for Confidential Information Analysis

Confidential information analysis can identify the text containing confidential information, thereby protecting organizations from the threat posed by leakage of confidential information. It is effective to build a confidential information analyzer based on a neural network. Most of the existing studies pursue high accuracy to design complex networks, ignoring speed and consumption. The optimal defense is to automatically analyze confidential information without compromising routine services. In this paper, we introduce a lightweight network, DSCNN, that can be adapted to low-resource devices. We also introduce two hyper-parameters to balance accuracy and speed. Our motivation is to simplify convolutions by breaking them down because the space dimension and channel dimension are not closely related in the convolutions. Experimental results on real-world data from WikiLeaks show that our proposed DSCNN performs well for confidential information analysis.

[1]  Tong Zhang,et al.  Deep Pyramid Convolutional Neural Networks for Text Categorization , 2017, ACL.

[2]  Chao Liu,et al.  A Two-Stage Model Based on BERT for Short Fake News Detection , 2019, KSEM.

[3]  Jian Sun,et al.  Identity Mappings in Deep Residual Networks , 2016, ECCV.

[4]  Xiang Zhang,et al.  Character-level Convolutional Networks for Text Classification , 2015, NIPS.

[5]  Liang Bin,et al.  Chinese Micro-Blog Sentiment Analysis Based on Multi-Channels Convolutional Neural Networks , 2018 .

[6]  Khudran Maeed Alzhrani,et al.  Towards Automating Big Texts Security Classification , 2018 .

[7]  Chao Liu,et al.  Sentiment Embedded Semantic Space for More Accurate Sentiment Analysis , 2018, KSEM.

[8]  Jiafeng Guo,et al.  CIDetector: Semi-Supervised Method for Multi-Topic Confidential Information Detection , 2020, ECAI.

[9]  Rob Law,et al.  Tourism demand forecasting: A deep learning approach , 2019, Annals of Tourism Research.

[10]  Tong Zhang,et al.  Semi-supervised Convolutional Neural Networks for Text Categorization via Region Embedding , 2015, NIPS.

[11]  Bo Chen,et al.  MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications , 2017, ArXiv.

[12]  Yann LeCun,et al.  Very Deep Convolutional Networks for Text Classification , 2016, EACL.

[13]  Tong Zhang,et al.  Effective Use of Word Order for Text Categorization with Convolutional Neural Networks , 2014, NAACL.

[14]  Wenpeng Yin,et al.  Multichannel Variable-Size Convolution for Sentence Classification , 2015, CoNLL.

[15]  Phil Blunsom,et al.  A Convolutional Neural Network for Modelling Sentences , 2014, ACL.

[16]  Philip S. Yu,et al.  Differentially Private Social Network Data Publishing , 2017 .

[17]  Helen Nissenbaum,et al.  VACCINE: Using Contextual Integrity For Data Leakage Detection , 2019, WWW.

[18]  Yoon Kim,et al.  Convolutional Neural Networks for Sentence Classification , 2014, EMNLP.

[19]  Rob Law,et al.  Exploring Tourist Dining Preferences Based on Restaurant Reviews , 2019 .

[20]  Cícero Nogueira dos Santos,et al.  Deep Convolutional Neural Networks for Sentiment Analysis of Short Texts , 2014, COLING.