Smart home technology (SHT), an Internet of Things (IoT) application, is a growing industry centered on the remote control of devices and networks that offers convenience, cost savings, energy efficiency, and improved quality of life. However, in the face of mounting evidence, several federal agencies and security experts have voiced concerns about the susceptibility of these networked devices to cyber-attacks. They are also susceptible to secure shell (SSH) brute force attacks, often followed by the propagation of malware through botnets. Recently, machine learning (ML) algorithms have been deployed for anomaly detection based on similarities and trends in network traffic. Thus, ML algorithms may be used to develop prediction models for detecting network attacks automatically. This study offers a comprehensive examination of the use of ML techniques to detect these two prevalent SHT network attacks, SSH brute force and botnet attacks.
