Abstract

The Internet of Things (IoT) has witnessed significant growth with the proliferation of connected devices in various domains. However, this rapid expansion has also led to an increase in security vulnerabilities, particularly in the form of botnet attacks. Botnets are networks of compromised devices controlled by malicious actors, and they can be leveraged to launch various cyber-attacks. Among the most infamous botnet attacks targeting IoT devices are the Gafgyt and Mirai botnets. These attacks exploit security weaknesses in IoT devices, compromising them and turning them into bots for executing large-scale attacks. The need for a reliable detection mechanism for IoT botnet attacks arises from the increasing frequency and severity of such attacks. As IoT devices continue to grow in number and become more integral to critical infrastructure and everyday life, the potential consequences of botnet attacks become more severe. These attacks can disrupt services, compromise sensitive data, and even pose physical risks. Therefore, it is crucial to develop effective methods to identify and mitigate IoT botnet attacks promptly. One such mechanism is the Random Forest Classifier, which is a machine learning algorithm known for its robustness and accuracy in classification tasks. Random Forest Classifier combines the predictions of multiple decision trees to make accurate predictions about the class labels of input data. This algorithm has been widely used in various domains, including cybersecurity, due to its ability to handle complex and high-dimensional datasets.

Description