Internet Monitoring using Snort and Naïve Bayes Method using Internet of Things (IoT)

This paper describes a novel technique for identifying malicious users using deep packet-sniffing using the "Snort" programme. How to track a person's online behavior and block hostile websites that are or could encourage the use of data piracy are used for tracking the unintentional malicious acts and preventing the specific user from visiting the particular website again. In this work, the Naive Bayes algorithm was used to predict attribute- classes utilizing training data-sets from NSLKDD in the KDD99 format and testing data collected from the DoS attack recording process on IoT-based devices. Naive Bayes has the benefit of requiring less training data, which makes it easier to get the estimated parameters required for classification. Using the findings of the research, it was possible to identify assaults on IoT devices. Snort tools are used to collect traffic records. The KDD99 format was then applied to the log's findings, and the Naive Bayes algorithm was used to analyze them. For testing purposes, data from the Raspberry Pi 3's IDS log process and a training dataset from NSLKDD in KDD99 format are both employed in this study