By Topic

Data-Adaptive Clustering Analysis for Online Botnet Detection

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

5 Author(s)
Xiaocong Yu ; Coll. of Inf. Sci. & Eng., Northeastern Univ., Shenyang, China ; Xiaomei Dong ; Ge Yu ; Yuhai Qin
more authors

Botnets have attracted lots of attention since botnet-based attacking is becoming one of the most serious threats on the Internet. Lots of approaches have been proposed to detect the presence of botnets. However, most of them just focus on offline detection methods by tracking the historical network traffic, which is not suitable for fast detection in the current environment. In this paper, we propose a new technique that can detect the botnet activities in an online fashion. We transform raw network traffic flows into “multi-dimensional feature streams”, adopt the sliding window to retain the continuous network traffic and select correlation analysis as the similarity measurement. A novel data-adaptive clustering technique is presented to group those feature streams that have high similarities. Hosts whose feature streams belong to the same cluster with high interior similarities will be regarded as suspected bot hosts. The experimental evaluations show that this approach can achieve online botnet detection efficiently.

Published in:

Computational Science and Optimization (CSO), 2010 Third International Joint Conference on  (Volume:1 )

Date of Conference:

28-31 May 2010