| Title | Vulnerability detection with deep learning |
| Publication Type | Conference Paper |
| Year of Publication | 2017 |
| Authors | Wu, F., Wang, J., Liu, J., Wang, W. |
| Conference Name | 2017 3rd IEEE International Conference on Computer and Communications (ICCC) |
| Keywords | compositionality, convolution, convolution neural network, Deep Learning, Human Behavior, long short term memory, machine learning, Metrics, Neural networks, pubcrawl, Resiliency, Software, Task Analysis, Tools, Training, vulnerability detection |
| Abstract | Vulnerability detection is an import issue in information system security. In this work, we propose the deep learning method for vulnerability detection. We present three deep learning models, namely, convolution neural network (CNN), long short term memory (LSTM) and convolution neural network -- long short term memory (CNN-LSTM). In order to test the performance of our approach, we collected 9872 sequences of function calls as features to represent the patterns of binary programs during their execution. We apply our deep learning models to predict the vulnerabilities of these binary programs based on the collected data. The experimental results show that the prediction accuracy of our proposed method reaches 83.6%, which is superior to that of traditional method like multi-layer perceptron (MLP). |
| DOI | 10.1109/CompComm.2017.8322752 |
| Citation Key | wu_vulnerability_2017 |
Vulnerability detection with deep learning