Collaborative detection and mitigation of DDoS in software-defined networks
This research presents the detection and mitigation of distributed denial of service (DDoS) in software defined networks (SDN). The proposed method consists of three modules: classifier module, mitigation module, and collaborative module. An ensemble classifier called V-NKDE is capable of detecting...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Published: |
Springer
2021
|
| Subjects: | |
| Online Access: | http://eprints.utm.my/id/eprint/95410/ http://dx.doi.org/10.1007/s11227-021-03782-9 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | This research presents the detection and mitigation of distributed denial of service (DDoS) in software defined networks (SDN). The proposed method consists of three modules: classifier module, mitigation module, and collaborative module. An ensemble classifier called V-NKDE is capable of detecting DDoS attacks accurately. The mitigation module blocks malicious traffics and purges entries of malicious traffic from the switch flow table. The collaborative module shares DDoS detection and mitigation rules among multiple SDN controllers using Redis Simple Message Queue mechanism. The proposed classifier performance validation on InSDN2020, CICIDS2017, NSL-KDD and UNSW-NB15 datasets. Furthermore we evaluated our proposed classifier in real traffic on an SDN simulation tested. The results show that the proposed method can detect DDoS attacks with high accuracy using an ensemble classifier, which performs better than single classifiers. More importantly, the false positive rate is greatly reduced, showing detection and mitigation of DDoS attacks across multi-controller domains with low controller overhead. |
|---|