.png){kind=icon}
.png){kind=icon}
Return
Deep Learning-Based Detection Mechanism for DDoS Attacks Targeting SDN Controller
.png){kind=icon}
PRE
AI
DOI：10.1007/s10922-026-10048-3.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
The rapid adoption of Software-Defined Networking (SDN) in cloud, IoT, and Big Data environments introduces significant security challenges, particularly for the SDN controller, which lacks built-in protection and remains vulnerable to Denial-of-Service (DDoS) attacks. This study proposes an enhanced deep learning-based detection mechanism for identifying multi-rate DDoS attacks in an SDN controller. The proposed mechanism is evaluated under two attack scenarios and achieves an average accuracy of 99.91% for high-rate and 99.21% for low-rate attacks when detecting DDoS flooding traffic. The results demonstrate the effectiveness and robustness of the proposed mechanism in protecting the SDN controller against DDoS attacks.
Keywords:
Cybersecurity attacks
SDN controller
Deep learning (DL)
Feature selection
Journal
IF:
3.9
Papers:
1.0K
Citations:
1.3K