Bot attack detection using various machine learning algorithms
Sanjay Madan, Shivani Arya, Divya Bansal, Sanjeev Sofat · 2021
With the rapid increase of Internet-of-Things devices globally, the cyber-attacks increase proportionately on such resource constraint devices, which have less memory and computational resources. Most of the attacks on the IoT infrastructure are botnet-based attacks. To develop an automated mitigation solution, there is a need to develop methods for the detection of bot attacks in the early stages of infection. In this study, proposed a machine learning-based method for the detection of bot attack through network flow data. The efficient feature selection and evaluation method is implemented for the development of scalable model with high accuracy. The various machine learning algorithms used to train the detection model and achieve around 95% of accuracy for detection of bot attack.