The DDoS attacks detection through machine learning and statistical methods in SDN

Dehkordi, Afsaneh Banitalebi; Aghaei, Mohammadreza Soltan; Boroujeni, Farsad Zamani

doi:10.1007/s11227-020-03323-w

Cited by 138 publications

(52 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [154], a solution for detecting low and high traffic volume DDoS attacks is presented. This solution has two types of thresholds, namely, static through entropy and dynamic through machine learning.…”

Section: ) Stateless Data Planementioning

confidence: 99%

A Survey of the Main Security Issues and Solutions for the SDN Architecture

et al. 2021

View full text Add to dashboard Cite

The software-defined networking (SDN) paradigm proposes the decoupling of control and data planes and a centralized software-oriented management approach based on a central controller, easing the development of new applications and services. These design principles pave the way for a more flexible, fast, and dynamic software-controlled network. However, in terms of security, the elements that comprise the SDN architecture present several vulnerabilities, which could be exploited by attackers to carry out malicious actions and thus affect the network and its services. Although for several years, some studies have already focused on identifying the weaknesses of the SDN layer structure, the nature of the attacks, and possible solutions for this paradigm, the literature contains few contributions that review and discuss this topic in an integral fashion. This paper provides a comprehensive, updated, and detailed review of the main security issues and mitigating measures for all layers and interfaces of the SDN architecture, classifying the contributions according to the STRIDE threat modeling methodology categories. Finally, this manuscript identifies, discusses, and synthesizes open challenges and future research directions in this area.

show abstract

Section: ) Stateless Data Planementioning

confidence: 99%

A Survey of the Main Security Issues and Solutions for the SDN Architecture

et al. 2021

View full text Add to dashboard Cite

show abstract

“…However, the authors did not compare the performance results with other related works. Dehkordi et al [134] proposed a detection method that makes use of statistical and ML approaches for DDoS detection. The implemented model aimed to detect HTTP application layer DDoS whether highor low-volume attacks.…”

Section: B Ddos Defense Systems Based On ML Techniques In Sdn Enviromentioning

confidence: 99%

Machine Learning Approaches for Combating Distributed Denial of Service Attacks in Modern Networking Environments

Aljuhani

2021

IEEE Access

View full text Add to dashboard Cite

“…Dehkordi et al [41] proposed a DDoS attack detection mechanism based on machine learning and the statistical method. The detection method consists of the collector, entropy, and classification.…”

Section: ) Data Planementioning

confidence: 99%

“…The stateful SD-IoT network has issues, whenever Open- Flow switch window size increases and becomes full, it was not able to inform the controller about the states [42]. In some approaches, only a single controller is detecting the DDoS attack, that may fail to receive a large number of unknown flow entries [41]. Our proposed system resolves these issues with the support of the multiple IoT controller.…”

Section: ) Data Planementioning

confidence: 99%

“…Statistical methods based on entropy techniques that use the threshold values of the network information with uncertainty, do not have detailed information about the malicious flow. For example, with dynamic threshold value has high FPR (False Positive Rate) [41], this issue is further resolved through classification, and as another example in which entropy of destination IP address based on threshold values [40] also does not locate specific nodes.…”

Section: ) Data Planementioning

confidence: 99%

See 1 more Smart Citation