Abstract: Malicious malware can exploit vulnerabilities in the internet computing environment without the users knowledge. Today, different types of malware exist in the Internet. Among them one of the malware is known as botnet which is frequently used for many cyber attacks and crimes in the Internet. The aim of this study is to develop a scalable botnet detection framework which will be able to identify and remove stealthy botnets from the real-world network traffic. Storm real time, distributed, reliable, fault-tolerant software is used in this work for analyzing the streams of data. Experimental results show that random forest has higher accuracy rate than fuzzy c-means but clustering algorithm is useful to detect the botnet in real time processing.
V. Vanitha, V.P. Sumathi, Sindhu Arumugam and Nandhini Selvam, 2016. Scalable Real Time Botnet Detection System for Cyber-Security. Asian Journal of Information Technology, 15: 670-675.