| An Efficient Attack Detection Framework in Software-Defined Networking using Intelligent Techniques |
| Paper ID : 1064-ICEEM2023 (R1) |
| Authors: |
|
Heba Ahmed Hassan *1, Ezz El-Din Hemdan2, Walid El-Shafai3, Mona Shokair4, Prof. Fathi Sayed1 1Department of Electronics and Communication Engineering, Faculty of Electronic Engineering, Menoufia University, Menouf 32952, Egypt 2Department of Computer Science and Engineering, Faculty of Electronic Engineering, Menoufia University, Menouf 32952, Egypt 3Department of Electronics and Communication Engineering, Faculty of Electronic Engineering, Menoufia University, Menouf 32952, Egypt. Security Engineering Laboratory, Department of Computer Science, Prince Sultan University, Riyadh 11586, Saudi Arabia 4Department of Electronics and Communication Engineering, Faculty of Electronic Engineering, Menoufia University, Menouf 32952, Egypt. Faculty of Electrical Engineering, 6 October University |
| Abstract: |
| Recently, Software-Defined Networking (SDN) architecture has offered great benefits due to the separation between the controller and network elements such as routers and switches. Unfortunately, the enormous growth of attacks hinders the wide adoption of SDNs. Intrusion Detection Systems (IDSs) are used as significant tools to detect and mitigate network anomalous attacks. In recent times, several deep learning models, such as Convolutional Neural Networks (CNNs) have been utilized for building IDSs in cyber security because they achieve the desired detection results. Nonetheless, little work has been introduced on IDS in SDN systems. When malicious traffic is identified in an SDN topology, the Artificial Intelligence (AI) module employs machine learning and deep learning algorithms to identify and stop the attack source. The architecture presented in this research allows for comparing several machine learning and deep learning classification techniques that can be used to identify different sorts of network attacks. The proposed framework is tested on the InSDN dataset using several learning models like Logistic Regression (LR), Naïve Bayes (NB), K-Nearest Neighbor (KNN), Decision Tree Classifier (DT), AdaBoost(AB), and Random Forest (RF) classifiers. In addition, deep learning algorithms such as Deep CNN, and Long Short Term Memory (LSTM) are considered. The results demonstrate that the proposed Deep CNN model for multi-class attack data achieves the highest accuracy of 99.85% compared to LR, NB, KNN, DT, AB, RF, and LSTM classifiers with accuracy levels of 98 %, 93 %, 97%, 90 %, 88 %, 95 %, and 88.31 %, respectively. |
| Keywords: |
| Intrusion Detection Systems (IDSs), Convolutional Neural Networks (CNN), Software-Defined Networking (SDN), and InSDN dataset. |
| Status : Paper Accepted |
