Nowadays, the development of technology, especially in the area of the Internet of Things (IoT), is proceeding at a dizzying pace. With this development comes an increasing number of threats that can affect IoT network users. Network traffic is increasingly becoming the target of various attacks, and the consequences of these attacks depend on the type of attack and the attacker's objectives. The purpose of the paper is to analyze the application of machine learning and artificial intelligence algorithms to analyze data for detecting anomalies and threats in IoT networks. The paper compares less complex machine learning algorithms with more advanced artificial intelligence methods in terms of performance and prediction accuracy. The research used the “RTIoT2022” 2022 dataset, which enabled the identification of specific patterns of attacks on IoT networks and the evaluation of the effectiveness of selected detection methods.