Comparative Analysis of DDoS Detection Techniques Based on Machine Learning in OpenFlow Network

Sumadi, Fauzi Dwi Setiawan; Aditya, Christian Sri Kusuma

doi:10.1109/isriti51436.2020.9315510

Cited by 3 publications

(9 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When a centralized control system is implemented in this manner, a security vulnerability is created that an attacker could exploit to change the topology directly connected to a controller. DDoS attacks can therefore be carried out both locally and globally [18].…”

Section: Background Studymentioning

confidence: 99%

“…Rahman, M. A. developed a framework to track anomalies that includes several steps, such as feature selection, data preprocessing, data analysis to apply various machine learning algorithms, training the dataset to algorithms, testing the dataset, and contrasting the results with various algorithmic approaches [18]. the creation of a classifier that can tell malicious packets apart from normal ones.…”

Section: Comparative Review Based On Frameworkmentioning

confidence: 99%

“…The researchers used the NSL-KDD dataset, which has been widely used in the DDoS detection industry [18]. A training dataset with 125,973 rows and a test dataset with 22,544 rows had previously been produced from the entire data set.…”

Section: Comparative Review Based On Datasetsmentioning

confidence: 99%

See 2 more Smart Citations

A Comparative Review on DDoS Attack Detection Using Machine Learning Techniques

Zerin Hasan Sahosh,

Azraf Faheem,

Marzana Bintay Tuba

et al. 2024

Malaysian J. Sci. Adv. Tech.

View full text Add to dashboard Cite

The rapid growth of the internet and the increasing reliance on digital infrastructures have posed significant challenges to cybersecurity. Among the other variants of attacks, Distributed Denial of Service (DDoS) attacks have emerged as one of the most destructive and common threats. These attacks disrupt or slow down network services by overwhelming the network infrastructure with a massive volume of malicious traffic. To effectively identify and mitigate DDoS attacks, machine learning techniques have been extensively employed in intrusion detection systems. Machine learning approaches offer the advantage of automating the detection process by learning patterns and characteristics of DDoS attacks from historical data. Researchers have explored various machine learning algorithms such as K-Nearest Neighbours (KNN), Support Vector Machine (SVM), Random Forest (RF), and Naïve Bayes to classify and detect DDoS attacks. These algorithms leverage features extracted from network traffic data, including packet size, packet delay patterns, and traffic behaviour, to differentiate between normal and malicious traffic.

show abstract

Section: Background Studymentioning

confidence: 99%

Section: Comparative Review Based On Frameworkmentioning

confidence: 99%

See 1 more Smart Citation

A Comparative Review on DDoS Attack Detection Using Machine Learning Techniques

Zerin Hasan Sahosh,

Azraf Faheem,

Marzana Bintay Tuba

et al. 2024

Malaysian J. Sci. Adv. Tech.

View full text Add to dashboard Cite

show abstract

“…Rapid Developments in computer network technology are currently experiencing significant changes, especially with the establishment of SDN [1]. SDN is the latest architecture that is used to replace the traditional scheme on the network.…”

Section: Introductionmentioning

confidence: 99%

“…While the NB algorithm had the worst accuracy rate among other algorithms with an accuracy rate of 79% on the controller and 66% on the switch. Furthermore, research [1] proposed a reactive application-based solution that could identify, detect, and mitigate attacks comprehensively. In his research, an application had been built using machine learning algorithms including, Support Vector Machine (SVM) with the Linear and RBF kernel, K-Nearest Neighbor (KNN), Decision Tree (DTC), Random Forest (RFC), Multi-Layer Perceptron (MLP), and Gaussian Naïve Bayes (GNB).…”

Section: Introductionmentioning

confidence: 99%

Low-Rate Attack Detection on SD-IoT Using SVM Combined with Feature Importance Logistic Regression Coefficient

Azmi

Sumadi

2022

KINETIK

View full text Add to dashboard Cite

The evolution of computer network technology is now experiencing substantial changes, particularly with the introduction of a new paradigm, Software Defined Networking (SDN). The SDN architecture has been applied in a variety of networks, including the Internet of Things (IoT), which is known as SD-IoT. IoT is made up of billions of networking devices that are interconnected and linked to the Internet. Since the SD-IoT was considered as a complex entity, several types of attack on vulnerabilities vary greatly and can be exploited by careless individuals. Low-Rate Distributed Denial of Service (LRDDoS) is one of the availability-based attack that may affect the SD-IoT integration paradigm. Therefore, it is necessary to have an Intrusion Detection System (IDS) to overcome the security hole caused by LRDDoS. The main objective of this research was the establishment of an IDS application for resolving LRDDoS attack using the SVM algorithm combined with the Feature Importance method, namely the Logistic Regression Coefficient. The implemented approach was developed to reduce the complexity or resource’s consumption during the classification process as well as increasing the accuracy. It could be concluded that the Linear kernel SVM algorithm acquired the highest results on the test schemes at 100% accuracy, but the training time required for this model was longer, about 23.6 seconds compared to the Radial Basis Function model which only takes about 1.5 seconds.

show abstract