Enhanced Network Threat Detection Using Machine Learning Ensemble Methods

View at publisher Summarise with VIRAT
Authors: Shaik Ameer, Sivaramakrishnan Rajendar
Cited by: 0
References: 18

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

With the increasing level and complexity of cyberattacks, the importance of accurate network intrusion detection systems is growing. We present a novel integrated deep learning and advanced machine learning ensemble-based anomaly detection system. We preprocess the CICIDS dataset and use a deep autoencoder to extract the latent features. We use the latent representation in a stacked ensemble comprising level 1 classifiers, XGBoost, CatBoost, and KNN, and a level 2 meta-learner, LightGBM, and Random Forest. Real-time detection of normal and attack traffic is deployed as a web application in Flask. The results achieved in this paper demonstrate the proposed solution is a robust and viable solution for contemporary network security systems as evidenced by the accuracy, positive predictive value, recall, and F1-score.

Fields of Study & Subjects

Network Security and Intrusion Detection Network Packet Processing and Optimization Internet Traffic Analysis and Secure E-voting

Publication details

Journal / source
International Conference on Communication, Computing and Electronics Systems (ICCCES)
Pages
439–444
Publication date
21 January 2026
Language
EN