Cyber Attack Detection on IoT Using Machine Learning

In recent years, there has been a rapid increase in the adoption of Internet of Things (IoT) devices due to their significant advantages in modern society. However, this surge has created a substantial opportunity for hackers to carry out malicious attacks. Detecting and mitigating these attacks necessitates the use of innovative techniques, given their severity. Machine learning, a subfield of Artificial Intelligence (AI, is a vital tool in addressing this issue. Techniques such as random forest, decision tree, k-nearest neighbors, support vector machine, logistic regression, extreme Gradient Boosting, Adaptive Boosting, and Gradient Boosting must be employed to effectively classify IoT attacks using two types of classification: binary and multiple classes. To evaluate the detection accuracy of various ML techniques, the IoTID20 dataset was created. We conducted a comparative analysis between our results and those obtained by others using similar ML techniques. The findings demonstrate that our models outperform others in terms of detection accuracy, both in binary and multiclass classifications.