Narrow Results

Software-defined network (SDN) is a new network structure, which has the characteristics of centralized management and programmable, and is widely used in the field of Internet of things. Distributed denial of service (DDoS) attack is one of the most threatening attacks in SDN network. How to effectively detect DDoS attacks has become a research hotspot in the field of SDN security management. Aiming at the above problems, this paper proposes a DDoS attack detection method based on Deep belief network (DBN) in SDN network architecture. By extracting the characteristics of OpenFlow switch flow table entries, DBN algorithm is trained to detect whether there are DDoS attacks. The experimental results show that the method is better than the other algorithms in accuracy, precision and recall.

The working approach is changing with the digitalization and advancement of technical tools, along with increased security risks. One of the most common and biggest threats that have been observed is attacks on communicational applications and networks. This threat is caused by denial of service (DoS) or distributed denial of service (DDoS). The behavior of the attacks performed through DoS and DDoS could be understood with an analysis of each step and attack process. A piece of brief information related to the attack through DoS or DDoS helps in understanding its effects, such as the development of countermeasures for the migration. Different types of networks, such as software-defined networks (SDN), virtual networks, and traditional networks, are classified in the model of DoS or DDoS. This chapter describes an analytical view of the different types of DoS or DDoS for network architecture. Mathematical modeling of the attacks through DoS or DDoS on different models, such as epidemic, hierarchical, analytical, and traffic, is described in the chapter.