Mass Removal of Botnet Attacks Using Heterogeneous Ensemble Stacking PROSIMA classifier in IoT

Abstract

In an Internet of Things (IoT) environment, any object, which is equipped with sensor node and other electronic devices can involve in the communication over wireless network. Hence, this environment is highly vulnerable to Botnet attack. Botnet attack degrades the system performance in a manner difficult to get identified by the IoT network users. The Botnet attack is incredibly difficult to observe and take away in restricted time. there are challenges prevailed in the detection of Botnet attack due to number of reasons such as its unique structurally repetitive nature, performing non uniform and dissimilar activities and invisible nature followed by deleting the record of history. Even though existing mechanisms have taken action against the Botnet attack proactively, it has been observed failing to capture the frequent abnormal activities of Botnet attackers .When number of devices in the IoT environment increases, the existing mechanisms have missed more number of Botnet due to its functional complexity. So this type of attack is very complex in nature and difficult to identify. In order to detect Botnet attack, Heterogeneous Ensemble Stacking PROSIMA classifier is proposed. This takes advantage of cluster sampling in place of conventional random sampling for higher accuracy of prediction. The proposed classifier is tested on an experimental test setup with 20 nodes. The proposed approach enables mass removal of Botnet attack detection with higher accuracy that helps in the IoT environment to maintain the reliability of the entire network.