ACADSTAFF UGM

CREATION
Title : XGBoost Classifier for DDOS Attack Detection in Software Defined Network using sFlow Protocol
Author :

NADHIR FACHRUL ROZAM (1) Dr. Mardhani Riasetiawan, SE Ak, M.T. (2)

Date : 0 2022
Keyword : Software Defined Network; sFlow; Distributed Denial of Service; Extreme Gradient Boosting Software Defined Network; sFlow; Distributed Denial of Service; Extreme Gradient Boosting
Abstract : In security perspective, SDN separates security concerns into Control Plane and Data Plane. The Control Plane responsible for managing the entire network centrally. Centralized in Software Defined Network (SDN) generates high vulnerability against the Distributed Denial of Service (DDOS) attack. When a Software Defined Network overwhelms by DDOS attack, both Control Plane and Data Plane will lack resources. If this is not detected early, it can cause the SDN network to fail to work. Using sFlow Protocol with the ability to capture the flow traffic in real-time, the data could be used to detect DDOS attacks. This sFlow sampling approach can reduce the workload of network by lower down processing and network overhead of switches. In this paper we use the Extreme Gradient Boosting (XGBoost), Support Vector Machine (SVM), Random Forest as detection methods. We use ONOS as SDN Controller and build the topology in GNS3. Prometheus as a time series database retrieves data from the sFlow Collector. The classifier then use the data from Prometheus for DDOS detection. For the dataset we use four different datasets. Datasets 1 and 2 with a total of 6109 data, each divided into 2 classes and 3 classes. Datasets 3 and 4 with a total data of 400488 are divided into 2 and 3 classes, respectively. The evaluation of the proposed system demonstrates XGBoost has higher accuracy than other methods using Dataset 4 as training set with 99.84% for test with dataset test set and 99.78% for real-time test.
Group of Knowledge : Ilmu Komputer
Original Language : English
Level : Internasional
Status :
Published
Document
No Title Document Type Action
1 paper-english version.pdf
Document Type : [PAK] Full Dokumen
[PAK] Full Dokumen View
2 full dokumen_compressed (2).pdf
Document Type : [PAK] Full Dokumen
[PAK] Full Dokumen View
3 XGBoost Classifier for DDOS Attack Detection in Software Defined Network using sFlow Protocol.pdf
Document Type : [PAK] Cek Similarity
[PAK] Cek Similarity View
4 Bukti Korepondensi.pdf
Document Type : [PAK] Bukti Korespondensi Penulis
[PAK] Bukti Korespondensi Penulis View