| Title | Vulnerability Severity Prediction With Deep Neural Network |
| Publication Type | Conference Paper |
| Year of Publication | 2019 |
| Authors | Liu, Kai, Zhou, Yun, Wang, Qingyong, Zhu, Xianqiang |
| Conference Name | 2019 5th International Conference on Big Data and Information Analytics (BigDIA) |
| Keywords | Communication networks, computer network security, convolution, convolutional neural nets, Cross Site Scripting, Data models, Deep Neural Network, deep neural networks, false negative rate, huge economic losses, Human Behavior, learning (artificial intelligence), machine learning, multiple deep learning methods, Network security, network security incidents, Neural networks, optimal CNN network, pubcrawl, recurrent convolutional neural networks, recurrent neural nets, Resiliency, Scalability, security, standard cross site scripting vulnerability text data, text categorization, text classification, TextRCNN, vulnerability risk levels, vulnerability severity prediction, vulnerability text classification evaluation, vulnerability text information, XSS vulnerability |
| Abstract | High frequency of network security incidents has also brought a lot of negative effects and even huge economic losses to countries, enterprises and individuals in recent years. Therefore, more and more attention has been paid to the problem of network security. In order to evaluate the newly included vulnerability text information accurately, and to reduce the workload of experts and the false negative rate of the traditional method. Multiple deep learning methods for vulnerability text classification evaluation are proposed in this paper. The standard Cross Site Scripting (XSS) vulnerability text data is processed first, and then classified using three kinds of deep neural networks (CNN, LSTM, TextRCNN) and one kind of traditional machine learning method (XGBoost). The dropout ratio of the optimal CNN network, the epoch of all deep neural networks and training set data were tuned via experiments to improve the fit on our target task. The results show that the deep learning methods evaluate vulnerability risk levels better, compared with traditional machine learning methods, but cost more time. We train our models in various training sets and test with the same testing set. The performance and utility of recurrent convolutional neural networks (TextRCNN) is highest in comparison to all other methods, which classification accuracy rate is 93.95%. |
| DOI | 10.1109/BigDIA.2019.8802851 |
| Citation Key | liu_vulnerability_2019 |
Vulnerability Severity Prediction With Deep Neural Network