Botnet detection and feature analysis using backpropagation neural network with bio-inspired algorithms Online publication date: Mon, 09-Jul-2018
by Jen-Li Liao; Kuan-Cheng Lin; Jyh-Yih Hsu
International Journal of Cognitive Performance Support (IJCPS), Vol. 1, No. 2, 2018
Abstract: Botnets has been the major type of cybercrime recently, the amount of infected computers gradually increasing each year. Many companies and schools are often troubled with problems, such as DDOS, phishing, spam, and stealing of personal data, because botnet is constantly changing its network structure, attack patterns and data transmission, making it more and more difficult to detect. In this paper, we proposed some new features to detect the botnet traffic, and we found the best solutions by using feature selection algorithm. These two methods are particle swarm optimisation and genetic algorithms, and by using backpropagation network as the classifier, we evaluate our subset feature on botnet detection that shows high detection rate, and we validate that own manufactured feature packet transmission time of regularity can be adopted, and the accuracy will change with the t-value.
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Cognitive Performance Support (IJCPS):
Login with your Inderscience username and password:
Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.
If you still need assistance, please email subs@inderscience.com
Our Blog 
Follow us on Twitter 
Visit us on Facebook