Revealing influenced selected feature for P2P botnet detection

Abstract

P2P botnet has become a serious security threat for computer networking systems. Botnet attack causes a great financial loss and badly impact the information and communication technology (ICT) system. Current botnet detection mechanisms have limitations and flaws to deal with P2P botnets which famously known for their complexity and scalable attack. Studies show that botnets behavior can be detected based on several detection features. However, some of the feature parameters may not represent botnet behavior and may lead to higher false alarm detection rate. In this paper, we reveal selected feature that influences P2P botnets detection. The result obtained by selecting features shows detection attack rate of 99.74%.