Choo, Yong Han (2023) Detection Of Distributed Denial-Of-Service (Ddos) Attack With Hyperparameter Tuning Based On Machine Learning Approach. Faculty of Computing, Universiti Malaysia Pahang Al-Sultan Abdullah.
|
Pdf
CA19088.pdf - Accepted Version Download (2MB) | Preview |
Abstract
Distributed Denial-of-Service (DDoS) attack is one of the common cyber threats that launched around the world to disrupt the traffic of a target by performing a flood of Internet traffic to overwhelm the target. DDoS attack becomes critical as it is hard to detect DDoS attack as becoming sophisticated from time to time in terms of attack techniques, hard in differentiating the normal traffic and attack traffic when the network traffic becomes heavy as filtering task will be disturbed during facing the heavy network traffic and limitations of machine learning techniques that cause misclassification. There are five selected machine learning techniques are identified such as DNN, KNN, SVM, NB and DT to detect the DDoS attack and proposed the best machine learning model in terms of accuracy, precision, recall, F1-Score, ROC-AUC Curve Area and Confusion Matrix. To conduct the study, a standard benchmark dataset DDoS Attack SDN Dataset is applied. EDA and Data Preprocessing are performed to ensure a clean dataset is produced for obtaining an accurate and meaningful detection performance results. Among the five models, DNN is the best model as it has shown 99.84% accuracy, 100.00% precision, 100.00% recall, 100.00% F1-Score and 99.86% ROC AUC Curve Area to detect DDoS attack.
| Item Type: | Undergraduates Project Papers |
|---|---|
| Additional Information: | SV: Wan Nurulsafawati Binti Wan Manan |
| Uncontrolled Keywords: | cyber threats |
| Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science |
| Faculty/Division: | Faculty of Computing |
| Depositing User: | Mr. Nik Ahmad Nasyrun Nik Abd Malik |
| Date Deposited: | 07 Feb 2024 04:21 |
| Last Modified: | 07 Feb 2024 04:21 |
| URI: | http://umpir.ump.edu.my/id/eprint/40198 |
| Download Statistic: | View Download Statistics |
Actions (login required)
 |
View Item |