DETECTION OF PEER-TO-PEER BOTNETS USING GRAPH MINING

Abstract

Peer-to-Peer (P2P) botnets are significant threats to the Internet. The botnet traffic is increasing rapidly every year and impacts the entire Internet. A P2P botnet is responsible for launching various malicious activities such as DDoS attacks, click fraud attacks, stealing confidential information from bank and government websites, etc. It is challenging to detect P2P botnets because of their high resiliency against detection. This paper proposes a method that uses a network communication graph from network flow data to detect botnets. Three graph-mining techniques are used to detect bot nodes individually. The method's final result is obtained by applying an ensemble algorithm to the results of the three graph-mining techniques. A synthetic dataset from a testbed is used to assess the method's performance. In addition, the method is evaluated using a publicly available dataset. Experimental results show that the method performs with an accuracy of 99.99%, a precision of 94.29%,and a recall of 98.02%, which is better than existing methods