Implementasi Sistem Deteksi dan Mitigasi Serangan Distributed Denial of Service (DDoS) menggunakan SVM Classifier pada Arsitektur Software-Defined Network (SDN)

Jodi Chris Jordan Sihombing (Fakultas Ilmu Komputer, Universitas Brawijaya)
Dany Primanita Kartikasari (Fakultas Ilmu Komputer, Universitas Brawijaya)
Adhitya Bhawiyuga (Fakultas Ilmu Komputer, Universitas Brawijaya)

Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Vol 3 No 10 (2019): Oktober 2019

Software-defined network (SDN) provides a promising architecture for future networks and can benefit from programmability on the controller to manage all behavior on the network. Apart from the advantages SDN has, there are challenges to SDN network security. Distributed Denial of Service (DDoS) is one of the attacks that can attack components that exist on the SDN architecture. In this study the detection and mitigation system of DDoS attacks was built to minimize DDoS attacks on SDN architecture using SVM Classifier. SVM is applied to the machine learning model to classify normal traffic and DDoS attack traffic based on features taken from flow entries. From the test results the system has been able to detect DDoS attacks with an average accuracy of 96.83% and an average detection time of 67.80 ms. In addition, the system can also reduce the number of DDoS attack packets sent to the victim host.