A DDoS Attack Detection Method Based on SVM in Software Defined Network

Ye, Jin; Xiang-yang, Cheng; Zhu, Jian; Feng, Luting; Song, Lina

doi:10.1155/2018/9804061

Cited by 234 publications

(136 citation statements)

References 11 publications

Supporting

Mentioning

135

Contrasting

Order By: Relevance

“…The results, as well as the ones reported in the literature, are summarized in Table 10. It can be seen from Table 10, that the proposed machine learning model with feature selection approaches, results in better performance in comparison with the results from [10,16,18,19,21]. It should be noted that similar studies in the literature used different datasets and different models.…”

Section: Receiver Operating Characteristic (Roc) Curvementioning

confidence: 87%

See 1 more Smart Citation

Detecting DDoS Attacks in Software-Defined Networks Through Feature Selection Methods and Machine Learning Models

2020

View full text Add to dashboard Cite

Software Defined Networking (SDN) offers several advantages such as manageability, scaling, and improved performance. However, SDN involves specific security problems, especially if its controller is defenseless against Distributed Denial of Service (DDoS) attacks. The process and communication capacity of the controller is overloaded when DDoS attacks occur against the SDN controller. Consequently, as a result of the unnecessary flow produced by the controller for the attack packets, the capacity of the switch flow table becomes full, leading the network performance to decline to a critical threshold. In this study, DDoS attacks in SDN were detected using machine learning-based models. First, specific features were obtained from SDN for the dataset in normal conditions and under DDoS attack traffic. Then, a new dataset was created using feature selection methods on the existing dataset. Feature selection methods were preferred to simplify the models, facilitate their interpretation, and provide a shorter training time. Both datasets, created with and without feature selection methods, were trained and tested with Support Vector Machine (SVM), Naive Bayes (NB), Artificial Neural Network (ANN), and K-Nearest Neighbors (KNN) classification models. The test results showed that the use of the wrapper feature selection with a KNN classifier achieved the highest accuracy rate (98.3%) in DDoS attack detection. The results suggest that machine learning and feature selection algorithms can achieve better results in the detection of DDoS attacks in SDN with promising reductions in processing loads and times.Sustainability 2020, 12, 1035 2 of 16As the control logic has been taken from local devices and become central, SDN is structured from a single spot and dynamically optimized [4]. Although certain security threats are general in computer networks, SDN has brought its own security threats. There are at least seven different threat vectors identified with SDN [5]. The most important threat vector for SDN is Distributed Denial of Service (DDoS) attacks. They can be against the controller in SDN or in the storage capacity of the flow table in the OpenFlow switch.The controller is exposed to DDoS attacks through the communication line between the controller and the data plane. DDoS attacks direct a large amount of traffic to the OpenFlow switch on the data plane. If packets arriving at the OpenFlow switch do not match with the flow input in the flow table (miss flow), packets are taken into the flow buffer. Then, they are transmitted to the controller with the Packet-In message to write a new rule. In this situation, the sources of the controller (memory, processor, bandwidth, etc.) remain incapable and the network becomes inoperative. In addition, the bandwidth of the communication line between the controller that is exposed to attack traffic and the OpenFlow switch is negatively affected. Therefore, network performance severely declines [6].The data plane is exposed to DDoS attacks through the flow table located in the net...

show abstract

Section: Receiver Operating Characteristic (Roc) Curvementioning

confidence: 87%

“…Ye et al [16] gathered data on network traffic from the transmission devices on the data plane by means of the controller. Six-tuple characteristic values related to DDoS attacks from the switch flow table were extracted to detect DDoS attacks by means of SVM.…”

Section: Ddos Attacks Against the Openflow Switchmentioning

confidence: 99%

Detecting DDoS Attacks in Software-Defined Networks Through Feature Selection Methods and Machine Learning Models

2020

View full text Add to dashboard Cite

show abstract

“…On the DDoS detection on SDN researches, some researchers use a neural network algorithm, but it is not practical enough to be applied. Therefore, SVM is more useful for an effective dataset [14]. The authors have used a SDN environment provided by mininet and a floodlight controller.…”

Section: Related Workmentioning

confidence: 99%

Analysis of Features Dataset for DDoS Detection by using ASVM Method on Software Defined Networking

Oo¹,

Kamolphiwong²,

Kamolphiwong³

et al. 2020

IJNDC

View full text Add to dashboard Cite

With the continuous development of networking environment, nowadays, there are many innovative technologies in computer network researches and industries. Most businesses use various mobile devices, cloud services and virtualization techniques in network environments [1]. Their usage is becoming the strongest evolution. The network programmability will be critical for business growth. Most of the today's network types are traditional networks. The traditional network management methods are device-bydevice and system by using manual configurations [2]. All devices are controlled and managed by human. If a new network device is added to the network, the device must be first configured. As a result, the network is not flexible and cannot be easily scale.

show abstract

“…Recently, research is focused more on mitigating DoS attacks directed against both infrastructure of SDN itself and devices behind it [13][14][15][16][17][18]. However, below we review the papers that are most related to our contribution, i.e., [19][20][21][22].…”

Section: Related Workmentioning

confidence: 99%

Network Threats Mitigation Using Software-Defined Networking for the 5G Internet of Radio Light System

Cabaj

Gregorczyk

Mazurczyk

et al. 2019

Security and Communication Networks

View full text Add to dashboard Cite

Currently 5G communication networks are envisioned to offer in a near future a wide range of high-quality services and unfaltering user experiences. In order to achieve this, several issues including security, privacy, and trust aspects need to be solved so that the 5G networks can be widely welcomed and accepted. Considering above, in this paper, we take a step towards these requirements by proposing a dedicated SDN-based integrated security framework for the Internet of Radio Light (IoRL) system that is following 5G architecture design. In particular, we present how TCP SYN-based scanning activities and DHCP-related network threats like Denial of Service (DoS), traffic eavesdropping, etc. can be detected and mitigated using such an approach. Enclosed experimental results prove that the proposed security framework is effective and efficient and thus can be considered as a promising defensive solution.

show abstract

A DDoS Attack Detection Method Based on SVM in Software Defined Network

Cited by 234 publications

References 11 publications

Detecting DDoS Attacks in Software-Defined Networks Through Feature Selection Methods and Machine Learning Models

Detecting DDoS Attacks in Software-Defined Networks Through Feature Selection Methods and Machine Learning Models

Analysis of Features Dataset for DDoS Detection by using ASVM Method on Software Defined Networking

Network Threats Mitigation Using Software-Defined Networking for the 5G Internet of Radio Light System

Contact Info

Product

Resources

About