Detection of Man in The Middle Attack in 5G IOT using Machine Learning

Detection is therefore a vital element of any wireless network's security solution. Consequently, a dependable wireless intrusion detection system capable of identifying Man-in-the-Middle attacks within the Internet of Things is shown here. In this study, empirical evidence is presented to support the notion that a Man-in-the-Middle attack results in a much longer delay than other forms of attacks. In order for organizations to properly protect their sensitive data, they require a way of forecasting MITM attacks that is both faster and more accurate. Our investigations into this occurrence will be oriented on enhancing our preparedness for future attacks of a similar sort. To identify Man-in-the-Middle (MITM) attacks, we examined a number of machine learning algorithms and evaluated them by applying them to a log collection gathered from Internet of Things devices. A variety of performance measures for models were the subject of study. The GNB methodology requires much less time for both prediction and testing than other methods such as KNN and Random Forest. With a probability of 99.6 percent, GNB is extremely likely to be true. As a result, the GNB method is enough for assessing the presence or absence of an MITM attack..