A new DDoS detection model using multiple SVMs and TRA

Authors:
Jungtaek Seo;Cheolho Lee;Taeshik Shon;Kyu-Hyung Cho;Jongsub Moon
Affiliations:
National Security Research Institute, Daejeon, Republic of Korea;National Security Research Institute, Daejeon, Republic of Korea;CIST, KOREA University, Seoul, Republic of Korea;CIST, KOREA University, Seoul, Republic of Korea;CIST, KOREA University, Seoul, Republic of Korea
Venue:
EUC'05 Proceedings of the 2005 international conference on Embedded and Ubiquitous Computing
Year:
2005

Citing 6
Cited 1

An introduction to Kolmogorov complexity and its applications (2nd ed.)

An introduction to Kolmogorov complexity and its applications (2nd ed.)
An introduction to support Vector Machines: and other kernel-based learning methods

An introduction to support Vector Machines: and other kernel-based learning methods
A Tutorial on Support Vector Machines for Pattern Recognition

Data Mining and Knowledge Discovery
Denial-of-Service Attacks Rip the Internet

Computer
Inferring internet denial-of-service activity

SSYM'01 Proceedings of the 10th conference on USENIX Security Symposium - Volume 10
MULTOPS: a data-structure for bandwidth attack detection

SSYM'01 Proceedings of the 10th conference on USENIX Security Symposium - Volume 10

Research on the Detection of Distributed Denial of Service Attacks Based on the Characteristics of IP Flow

NPC '08 Proceedings of the IFIP International Conference on Network and Parallel Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Recently, many attack detection methods adopts machine learning algorithm to improve attack detection accuracy and automatically react to the attacks. However, the previous mechanisms based on machine learning have some disadvantages such as high false positive rate and computing overhead. In this paper, we propose a new DDoS detection model based on multiple SVMs (Support Vector Machine) in order to reduce the false positive rate. We employ TRA (Traffic Rate Analysis) to analyze the characteristics of network traffic for DDoS attacks. Experimental results show that the proposed model is a highly useful classifier for detecting DDoS attacks.