Classification of Network Traffic Using Machine Learning Techniques

Author(s)	Mr. Adit Tejaskumar Vyas, Prof. Prashant B. Swadas, Dr. Narendra M. Patel, Mr. Satyam Raval
Country	India
Abstract	Cybersecurity threats, including zero-day exploits, SQL injection, and cross-site scripting, require advanced detection mechanisms beyond traditional signature-based systems. This paper evaluates eight machine learning models—Support Vector Classifier, Gaussian Naïve Bayes, K-Nearest Neighbors, Random Forest, Multi-Layer Perceptron, Convolutional Neural Network, Long Short-Term Memory, and Gated Recurrent Unit—for intrusion detection and web application security. Using a dataset with 175,341 network traffic records, the models were assessed on accuracy, precision, recall, and F1 score. Random Forest achieved the highest test accuracy (98.84%) and F1 score (99.15%), though overfitting was noted. Deep learning models like GRU and LSTM excelled in capturing temporal patterns. Vulnerability assessment complemented machine learning for detecting web vulnerabilities. Results suggest Random Forest and deep learning models enhance intrusion detection, with future work focusing on modern datasets and hybrid systems.
Keywords	Intrusion Detection, Machine Learning, Cybersecurity, Web Application Security, Anomaly Detection
Field	Computer > Network / Security
Published In	Volume 7, Issue 3, May-June 2025
Published On	2025-05-16
DOI	https://doi.org/10.36948/ijfmr.2025.v07i03.44917
Short DOI	https://doi.org/g9kfvd

About IJFMR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9687-828-838	editor@ijfmr.com

International Journal For Multidisciplinary Research