ONOS Flood Defender: An Intelligent Approach to Mitigate DDoS Attack in SDN

Abstract

Software-Defined Networking (SDN) has made its place in the networks as new technology. SDN's programmable behavior enables it to change behavior on the fly, provides instructions for the task's automatic performance, dynamic scaling, and service integration. These advantages have made SDN necessary in networks. However, SDN suffers from the threat of DDoS attack. We have developed an approach to mitigate these threats by creating an ONOS Flood Defender Application (OFD App). This app effectively detects DDoS attack using supervised and ensemble machine learning techniques and mitigates them by tracebacking the attack traffic to its origin. Our results show that ensemble machine learning techniques perform better than single machine learning algorithm to detect DDoS attack. Random Forest classifier (RFC), an ensemble technique, performs best with the highest accuracy of 99.3% in detecting DDoS attack, followed by XGBoost classifier with an accuracy of 99%. The proposed framework of the OFD app is implemented in a Mininet emulator and ONOS SDN controller. The application performs effectively in terms of time, accuracy, and overhead of the system. Our app efficiently mitigates the attacks, thereby preventing a tremendous amount of damage to legitimate users.

Joint Selfattention-SVM DDoS Attack Detection and Defense Mechanism Based on Self-Attention Mechanism and SVM Classification for SDN Networks

“…Attackers generally use the same IP protocol to attack the network, which will reduce the randomness of the network IP protocol. [26]. Therefore, the entropy value of IP protocols is also an important indicator.…”

An efficient approach to detect distributed denial of service attacks for software defined internet of things combining autoencoder and extreme gradient boosting with feature selection and hyperparameter tuning optimization

“…Authors of Reference [40] developed a method for addressing DDoS attacks in SDN networks by setting the ONOS Flood Defender Application, which employs supervised and ensemble machine learning techniques such as MLP, SVM, KNN, XGBoost, AdaBoost, RF, Bagging classifier, and Gradient Boosting (GB). This method uses the correlation matrix and DT technique to handle the feature selection process and K ‐fold cross‐validation for optimization.…”

“…Among these approaches, AEs have demonstrated promise in identifying anomalies in network traffic patterns, 34 while XGBoost is a machine learning algorithm that performs well in classification tasks related to the DDoS area. 37,40 Additionally, optimizing feature selection and hyperparameters can further enhance the performance of machine learning algorithms. Feature selection entails identifying the most relevant features in the dataset, while hyperparameter tuning involves selecting the best combination of hyperparameters for the model.…”

“…Machine learning‐based approaches have been proposed for detecting DDoS attacks in SDN‐enabled IoT networks as a solution. Among these approaches, AEs have demonstrated promise in identifying anomalies in network traffic patterns, 34 while XGBoost is a machine learning algorithm that performs well in classification tasks related to the DDoS area 37,40 . Additionally, optimizing feature selection and hyperparameters can further enhance the performance of machine learning algorithms.…”

A novel machine learning‐based classification approach to prevent flow table overflow attack in Software‐Defined Networking

“…Naziya et al 37 suggested the model called ONOS flood defender model to mitigate a DDoS attack in SDN. The machine learning approaches in the ensemble model in this application detect the DDoS attack more efficiently.…”