Intrusion Detection System Using Machine Learning Techniques

Author

Deepalika.R , Ms. M.Suriya

Abstract

Intrusion Detection Systems (IDS) are vital cybersecurity mechanisms that monitor network traffic to detect suspicious, unauthorized, or malicious activities. With the increasing dependence on internet technologies, cloud services, and digital communication, cyber threats such as malware attacks, denial-of-service attacks, unauthorized access, and insider threats have become more frequent and sophisticated. Traditional protection systems such as firewalls and antivirus software are not always sufficient to identify evolving attacks. This project presents a machine learning-based Intrusion Detection System that enhances network security by classifying traffic as normal or malicious using Random Forest classification. The system involves data preprocessing, feature extraction, model training, testing, and deployment through a Flask-based interface. Random Forest was selected due to its high accuracy, robustness, and reduced overfitting. Experimental analysis demonstrates strong performance in detecting abnormal traffic patterns while minimizing false positives. This system provides an efficient, automated, and scalable approach to modern network protection. Keywords Intrusion Detection System, Machine Learning, Cybersecurity, Random Forest, Flask, Network Traffic Analysis, Classification, Feature Selection

Keywords

Intrusion Detection, Machine Learning

Full Text:

Download Paper PDF

References