• Journal of KIISE:Information Networking
• /
• v.35 no.6
• /
• pp.474-481
• /
• 2008

Scanning worm increases network traffic load and result in severe network congestion because it is a self-replicating worm and send copies of itself to a number of hosts through the Internet. So an early detection system which can automatically detect scanning worms is needed to protect network from those attacks. Although many studies are conducted to detect scanning worms, most of them are focusing on the method using packet header information. The method using packet header information has long detection delay since it must examine the header information of all packets entering or leaving the network. Therefore we propose an algorithm to detect scanning worms using network traffic characteristics such as variance of traffic volume, differentiated traffic volume, mean of differentiated traffic volume, and product of mean traffic volume and mean of differentiated traffic volume. We verified the proposed algorithm by analyzing the normal traffic captured in the real network and the worm traffic generated by simulator. The proposed algorithm can detect CodeRed and Slammer which are not detected by existing algorithm. In addition, all worms were detected in early stage: Slammer was detected in 4 seconds and CodeRed and Witty were detected in 11 seconds.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.41 no.2
• /
• pp.277-284
• /
• 2016

Various network attacks such as DDoS(Distributed Denial of service) and orm are one of the biggest problems in the modern society. These attacks reduce the quality of internet service and caused the cyber crime. To solve the above problem, signature based IDS(Intrusion Detection System) has been developed by network vendors. It has a high detection rate by using database of previous attack signatures or known malicious traffic pattern. However, signature based IDS have the fatal weakness that the new types of attacks can not be detected. The reason is signature depend on previous attack signatures. In this paper, we propose a k-means clustering based malicious traffic detection method to complement the problem of signature IDS. In order to demonstrate efficiency of the proposed method, we apply the bayesian theorem.