DDoS Attack Detection Approaches in on Software Defined Network

【Author】 Muzafar, Saira; Jhanjhi, N. Z.; Khan, Navid Ali; Ashfaq, Farzeen

【Source】2022 14TH INTERNATIONAL CONFERENCE ON MATHEMATICS, ACTUARIAL SCIENCE, COMPUTER SCIENCE AND STATISTICS (MACS)

【影响因子】

【Abstract】Software Defined Networking (SDN) is a new network paradigm to address the limitations of vertically integrated conventional networks in context of scalability, Quality of Service, flexibility, and security. SDN isolates the data plane from the control plane and the controller dynamically manages the network activities solely while the switches in the data plane just forward data packets as per the rules set by the controller. With the development of SDN, network security can be done in a more efficient and adaptable way. But the centralized controller, the control-data interface, and the control-application interface are all problems with the way SDN was built from the start. Intruders can use these weaknesses to launch many kinds of attacks to retard the network performance, specifically all layers of SDN architecture are endangered to Distributed Denial of Service (DDoS) attacks. In this paper, we discuss the popular DDoS attack detection approaches in SDN such as statistical, blockchain, machine learning and deep learning.

【Keywords】Distributed Denial of service (DDoS); Software Defined Networks (SDN); Blockchain; Entropy; Machine Learning (ML); Deep Learning (DL); Network Security

【发表时间】2022

【收录时间】2023-06-12

【文献类型】

【主题类别】

--