SVM based packet marking technique for traceback on malicious DDoS traffic

Authors:
Hyung-Woo Lee
Affiliations:
Div of Computer, Information and Software, Hanshin University, Osan, Gyunggi, Korea
Venue:
ICOIN'06 Proceedings of the 2006 international conference on Information Networking: advances in Data Communications and Wireless Networks
Year:
2006

Citing 4
Cited 1

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
Tracing Network Attacks to Their Sources

IEEE Internet Computing
Denial-of-Service Attacks Rip the Internet

Computer

DDoS attack detection using K-Nearest Neighbor classifier method

Telehealth/AT '08 Proceedings of the IASTED International Conference on Telehealth/Assistive Technologies

Quantified Score

Hi-index	0.00

Visualization

Abstract

Distributed Denial-of-Service(DDoS) attack can be done by generating a large volume of traffic through spoofing the IP address of DoS attacker The e-mail based attack is also similar with existing DDoS attack in network traffic status In response to such attacks, IP traceback technology has been proposed For example, the method identifies the source of a spoofed e-mail attack and restructures the path on the network through which the attacking packet has been transmitted This study proposed an improved marking technique that identifies DDoS traffics with TTL information at routers by applying the SVM module for malicious traffic control and cope with DDoS attack packets efficiently According to the result of experiments, the proposed technique reduced network load and improved filter/traceback performance.