AN EFFICIENT INTRUSION DETECTION SYSTEMS USING MACHINE LEARNING MODELS
Research Scholar, Department of Computer & Information Science, Annamalai University
Assistant Professor/Programmer, Department of Computer & Information Science
Annamalai University, Email: email@example.com
The global market takes place on the Internet. A computer network will undoubtedly be necessary for any organization to be successful. However, security becomes a major concern when connecting your business to a network, as your data is more vulnerable to attacks from hostile individuals. An intrusion detection system (IDS) comes in handy in this situation. In this article, we employ Random Forest classifier and Naive Bayes classifier to swiftly identify threats in an IDS because to the vastness of the CICIDS2017 dataset. The model test was performed in Python. The CICIDS2017 dataset was used to test our technique and the results show that the Random Forest classification achieves the highest accuracy for training and testing.
Keywords: Random Forest classifier, Naïve Bayes, Intrusion Detection Systems, CICIDS2017