| Issue |
ITM Web Conf.
Volume 47, 2022
2022 2nd International Conference on Computer, Communication, Control, Automation and Robotics (CCCAR2022)
|
|
|---|---|---|
| Article Number | 02042 | |
| Number of page(s) | 5 | |
| Section | Algorithm Optimization and Application | |
| DOI | https://doi.org/10.1051/itmconf/20224702042 | |
| Published online | 23 June 2022 | |
Research on deep learning method of intrusion attack prediction in software defined network
1 Changchun College of Electronic Technology, Changchun 130000, China
2 Network management center of China Mobile Communication Group Jilin Co., Ltd, Changchun 130012, China
* Corresponding author: 8624949@qq.com
At present, with the increase of the number of network attacks, in the software defined network, the controller is equivalent to the brain, which is an entity with a complete view of the network. When the attacker directs the malicious traffic to the controller, it may lead to the paralysis of the whole network. Therefore, although there are many solutions for intrusion detection, the attack prediction of network intrusion is still a problem worthy of study. This paper proposes a deep learning model based on gating loop unit (Gru) to identify and prevent intrusion attacks. The model can deeply learn the dependencies of security alarm sequences, and use data sets to evaluate the model. Experiments show that it can show the significant improvement of attack detection.
Key words: Software defined network / Deep learning / Gated circulation unit
© The Authors, published by EDP Sciences, 2022
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.