Feature Extraction Based IoT Botnet Detection Using Machine Learning Technique

Abstract

In recent years, there has been a proliferation of IoT (Internet of Things) devices and its enabling technologies in industries, product flow management, healthcare, transportation and other smart environments. The provision of IoT devices with IP (Internet Protocol) address allows for communication between these cyber-physical systems without any intervention. Lack of security on these end devices has led to many attacks like denial-of-service, Botnets, identity theft and data theft attacks. Botnets are one of the most serious threats to the Internet security and one of the most challenging topics within the fields of computer and network security today. Machine learning techniques can combats cyber-attacks by detection and prevention of these Botnets. In this paper, we explore on Botnet attacks that is prevalent in IoT devices as well as this paper presents a new feature combination based approach for botnet detection.  Various features like generic features, statistical & subnet features have extracted during feature extraction. Than ML methods has been applied on combination of feature set. The proposed method has achieved average accuracy around 99.8%. The developed method has also been evaluated on various machine learning models.