A Comparative Study of Decision Tree and Naïve Bayes Algorithms for Network Intrusion Detection
Year: 2026
Type: article
Abstract: A network intrusion is any unauthorized access to a computer network. For detecting a network intrusion, the defenders should have a clear understanding of how attacks work. In a network environment, intrusions possess a major security issue which can be an unauthorized activity on a computer network which is generally difficult to detect. Through this project we aim to monitor computer network for malicious activity using Intrusion Detection System(IDS). In this work, we aim to use Supervised Machine Learning Algorithms such as Naive Bayes Classifier and Decision Tree Classifiers, and compare their output and efficiency. The machine learning algorithms are used on a labelled dataset, which classifies the connections as good or bad. As a result, the accuracy of the classification result has to be maximized by maintaining low false-negative and low falsepositive rates.
Authors: Richa Kirad, Diwakar Tripathi
Language: English
Subfield: Computer Networks and Communications
Field: Computer Science
Domain: Physical Sciences
Open Access status: diamond
OpenAlex ID: W7233851369
