| Title | Detection of DDoS Based on Gray Level Co-Occurrence Matrix Theory and Deep Learning |
| Publication Type | Conference Paper |
| Year of Publication | 2020 |
| Authors | Shi, Jiayu, Wu, Bin |
| Conference Name | 2020 5th International Conference on Mechanical, Control and Computer Engineering (ICMCCE) |
| Date Published | Dec. 2020 |
| Publisher | IEEE |
| ISBN Number | 978-1-6654-2314-4 |
| Keywords | Classification algorithms, composability, convolutional neural network, Data processing, DDoS attack detection, Deep Learning, denial-of-service attack, Distributed databases, feature extraction, Gray Level Co-occurrence Matrix, Human Behavior, Metrics, pubcrawl, raw data flow, resilience, Resiliency, statistical analysis |
| Abstract | There have been researches on Distributed Denial of Service (DDoS) attack detection based on deep learning, but most of them use the feature data processed by data mining for feature learning and classification. Based on the original data flow, this paper combines the method of Gray Level Co-occurrence Matrix (GLCM), which not only retains the original data but also can further extract the potential relationship between the original data. The original data matrix and the reconstructed matrix were taken as the input of the model, and the Convolutional Neural Network(CNN) was used for feature learning. Finally, the classifier model was trained for detection. The experimental part is divided into two parts: comparing the detection effect of different data processing methods and different deep learning algorithms; the effectiveness and objectivity of the proposed method are verified by comparing the detection effect of the deep learning algorithm with that of the statistical analysis feature algorithm. |
| URL | https://ieeexplore.ieee.org/document/9421617 |
| DOI | 10.1109/ICMCCE51767.2020.00354 |
| Citation Key | shi_detection_2020 |
Detection of DDoS Based on Gray Level Co-Occurrence Matrix Theory and Deep Learning