A4 Article in conference proceedings
Reinforcement Learning for Attack Mitigation in SDN-enabled Networks (2020)
Zolotukhin, M., Kumar, S., & Hämäläinen, T. (2020). Reinforcement Learning for Attack Mitigation in SDN-enabled Networks. In F. De Turck, P. Chemouil, T. Wauters, M. Faten Zhani, W. Cerroni, R. Pasquini, & Z. Zhu (Eds.), NetSoft 2020 : Proceedings of the 2020 IEEE Conference on Network Softwarization. Bridging the Gap Between
AI and Network Softwarization (pp. 282-286). IEEE. https://doi.org/10.1109/NetSoft48620.2020.9165383
JYU authors or editors
Publication details
All authors or editors: Zolotukhin, Mikhail; Kumar, Sanjay; Hämäläinen, Timo
Parent publication: NetSoft 2020 : Proceedings of the 2020 IEEE Conference on Network Softwarization. Bridging the Gap Between
AI and Network Softwarization
Parent publication editors: De Turck, Filip; Chemouil, Prosper; Wauters, Tim; Faten Zhani, Mohamed; Cerroni, Walter; Pasquini, Rafael; Zhu, Zuqing
Conference:
- IEEE Conference on Network Softwarization
Place and date of conference: Virtual conference (Ghent, Belgium), 29.6.-3.7.2020
eISBN: 978-1-7281-5684-2
Publication year: 2020
Pages range: 282-286
Publisher: IEEE
Publication country: United States
Publication language: English
DOI: https://doi.org/10.1109/NetSoft48620.2020.9165383
Publication open access: Not open
Publication channel open access:
Publication is parallel published (JYX): https://jyx.jyu.fi/handle/123456789/93737
Abstract
With the recent progress in the development of low-budget sensors and machine-to-machine communication, the Internet-of-Things has attracted considerable attention. Unfortunately, many of today's smart devices are rushed to market with little consideration for basic security and privacy protection making them easy targets for various attacks. Unfortunately, organizations and network providers use mostly manual workflows to address malware-related incidents and therefore they are able to prevent neither attack damage nor potential attacks in the future. Thus, there is a need for a defense system that would not only detect an intrusion on time, but also would make the most optimal real-time crisis-action decision on how the network security policy should be modified in order to mitigate the threat. In this study, we are aiming to reach this goal relying on advanced technologies that have recently emerged in the area of cloud computing and network virtualization. We are proposing an intelligent defense system implemented as a reinforcement machine learning agent that processes current network state and takes a set of necessary actions in form of software-defined networking flows to redirect certain network traffic to virtual appliances. We also implement a proof-of-concept of the system and evaluate a couple of state-of-art reinforcement learning algorithms for mitigating three basic network attacks against a small realistic network environment.
Keywords: information networks; safety and security; data security; cyber attacks; anomalies; machine learning
Free keywords: network security; machine learning; reinforcement learning; software-defined networking; network function virtualization
Contributing organizations
Ministry reporting: Yes
Reporting Year: 2020
JUFO rating: 1