Distributed Denial of Service detection using hybrid machine learning technique
Distributed Denial of Service (DDoS) is a major threat among many security issues. To overcome this problem, many studies have been carried out by researchers, however due to inefficiency of their techniques in terms of accuracy and computational cost, proposing an efficient method to detect DDoS at...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Conference or Workshop Item |
| Published: |
IEEE (IEEE Xplore)
2014
|
| Online Access: | http://psasir.upm.edu.my/id/eprint/39735/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Universiti Putra Malaysia |
| Summary: | Distributed Denial of Service (DDoS) is a major threat among many security issues. To overcome this problem, many studies have been carried out by researchers, however due to inefficiency of their techniques in terms of accuracy and computational cost, proposing an efficient method to detect DDoS attack is still a hot topic in research. Current paper proposes architecture of a detection system for DDoS attack. Genetic Algorithm (GA) and Artificial Neural Network (ANN) are deployed for feature selection and attack detection respectively in our hybrid method. Wrapper method using GA is deployed to select the most efficient features and then DDoS attack detection rate is improved by applying Multi-Layer Perceptron (MLP) of ANN. Results demonstrate that the proposed method is able to detect DDoS attack with high accuracy and deniable False Alarm. |
|---|