Machine Learning Enhanced Intrusion Detection for Cybersecurity
P. S. Kavya
Department of Computer Science and Engineering
Panimalar Institute of Technology
Chennai, India
kavyaprakashpsk@gmail.com
Mrs. B. Bala Abirami
Assistant Professor
Department of Computer Science and Engineering
Panimalar Institute of Technology
Chennai, India
bala.bami@gmail.com
E. Srinidhi
Department of Computer Science and Engineering
Panimalar Institute of Technology
Chennai, India
srinidhielangoan@gmail.com
Dr. D. Lakshmi
Associate Professor and Head
Department of Computer Science and Engineering
Panimalar Institute of Technology
Chennai, India
csehod@pit.ac.in
K. Poojitha
Department of Computer Science and Engineering
Panimalar Institute of Technology
Chennai, India
poojithapooji191103@gmail.com
M. Abirami
Assistant Professor and Supervisor
Department of Computer Science and Engineering
Panimalar Institute of Technology
Chennai, India
swagathajaisathish@gmail.com
Abstract—In the modern digital landscape, AI-Driven Intrusion Detection plays a vital role in enhancing cybersecurity by using machine learning techniques to identify and prevent potential threats. This project involves developing an intelligent intrusion detection system that uses machine learning algorithms to detect network anomalies and intrusions effectively. The data preprocessing phase includes cleaning, normalization, and feature selection to improve the dataset quality for optimal machine learning model performance. Data visualization techniques, such as heatmaps, pair plots, and histograms, are employed to understand data distributions and correlations between features. Three machine learning algorithms are implemented and compared based on their accuracy, precision, recall, and F1-score, with the best-performing model selected for deployment. The chosen model is then integrated with the Django framework to create a user-friendly web application, allowing monitoring, prediction of network intrusions, and visualization of security alerts for enhanced cybersecurity management.
Keywords—The proposed methods include Machine Learning, Intrusion Detection Systems (IDS), Cyber Security, Network Traffic Analysis, Anomaly identification, Classification, Pattern recognition, Supervised Learning and Feature Engineering