View article

The usage of Internet of Things (IoT) devices is getting unavoidable lately, from handheld devices to factory automated machines and even IoT embedded automotive vehicles. On average, 100+ devices are connected to the IoT world per second, and the volume of data generated by these devices and added to the space is just too enormous. The value of the data costs more, and sometimes it is invaluable, and it may pull over the cybercriminals and eventually increases the number of cybercrimes. Therefore, the need to identify malware in IoT is a timely requirement. This research work applies Machine Learning (ML) models and yields an efficient lead to identifying the IoT malware using forensic analysis of their network traffic features by selecting the foremost unique features and combining them with the binary features of the malware families. An outsized dataset with many network traffic collections used various …