Hybrid Approach for Botnet Detection Using K-Means and K-Medoids with Hopfield Neural Network

Abstract

In the last few years, a number of attacks and malicious activities have been attributed to common channels between users. A botnet is considered as an important carrier of malicious and undesirable briskness. In this paper, we propose a support vector machine to classify botnet activities according to k-means, k-medoids, and neural network clusters. The proposed approach is based on the features of transfer control protocol packets. System performance and accuracy are evaluated using a predefined data set. Results show the ability of the proposed approach to detect botnet activities with high accuracy and performance in a short execution time. The proposed system provides 95.7% accuracy rate with a false positive rate less than or equal to 3%.