ABSTRACT
Wireless communication is one of the most substantial types of communication nowadays, leading to the IoT revolution and increasing demand for IoT networks. On the other hand, this demand also leads to an increase in the number of resource-constrained devices, which creates a new problem related to vulnerabilities to attacks. The handling of attacks on IoT devices must be closely monitored due to resource limitations for these devices, which makes research in this field important. Many intrusion detection systems have been improved by using machine learning models that classify data as normal or abnormal and use evaluation parameters such as accuracy, f1-score, and precision to assess their performance. One of the most important steps in building a good intrusion detection system is feature selection, which can help improve the reasonable classification of data. This paper discusses the latest research on using machine learning techniques for intrusion detection systems. It examines various prominent algorithms and provides further analysis on their appropriateness. CICIDS2017 dataset is used to evaluate the robustness and determinism of intrusion detection system models.
