Home / Current Issue / Paper 1718202
Development of an AI-Enhanced Intrusion Detection System for Detecting Zero-Day Attacks in Enterprise Networks
Subject area: Science,Engineering and Technology · Area of research: AI IDS for Zero-Day Detection
DOI: https://doi.org/10.64388/IREV9I11-1718202
Abstract
Zero-day attacks pose a significant threat to modern enterprise networks because they can exploit previously unknown vulnerabilities before security patches or signatures are available. Traditional intrusion detection systems (IDS), which rely primarily on signature-based detection, are inadequate for identifying such emerging threats. This paper presents the development of an AI-enhanced hybrid intrusion detection system designed to improve the detection of zero-day attacks in enterprise environments. The proposed system integrates machine learning and deep learning techniques within a hybrid framework that combines anomaly-based and misuse-based detection mechanisms. Network traffic data are subjected to preprocessing operations including feature extraction, normalization, and dimensionality reduction before classification using supervised and unsupervised learning models. Experimental evaluation demonstrates that the proposed IDS achieves higher detection accuracy and lower false positive rates compared to conventional IDS approaches. The results confirm that artificial intelligence significantly enhances enterprise security by enabling adaptive and real-time threat detection. This study contributes a practical and scalable framework for deploying intelligent intrusion detection systems capable of responding effectively to evolving cyber threats.
Keywords
Intrusion Detection System, Zero-Day Attacks, Artificial Intelligence, Machine Learning, Deep Learning, Enterprise Networks, Cybersecurity.
How to cite this paper
@article{1718202,
author = {Emmanuel Udeme Edet, Dr. Nelson Ogbogu},
title = {Development of an AI-Enhanced Intrusion Detection System for Detecting Zero-Day Attacks in Enterprise Networks},
journal = {Iconic Research And Engineering Journals},
year = {2026},
volume = {9},
number = {11},
pages = {4830-4833},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1718202.pdf},
abstract = {Zero-day attacks pose a significant threat to modern enterprise networks because they can exploit previously unknown vulnerabilities before security patches or signatures are available. Traditional intrusion detection systems (IDS), which rely primarily on signature-based detection, are inadequate for identifying such emerging threats. This paper presents the development of an AI-enhanced hybrid intrusion detection system designed to improve the detection of zero-day attacks in enterprise environments. The proposed system integrates machine learning and deep learning techniques within a hybrid framework that combines anomaly-based and misuse-based detection mechanisms. Network traffic data are subjected to preprocessing operations including feature extraction, normalization, and dimensionality reduction before classification using supervised and unsupervised learning models. Experimental evaluation demonstrates that the proposed IDS achieves higher detection accuracy and lower false positive rates compared to conventional IDS approaches. The results confirm that artificial intelligence significantly enhances enterprise security by enabling adaptive and real-time threat detection. This study contributes a practical and scalable framework for deploying intelligent intrusion detection systems capable of responding effectively to evolving cyber threats.},
keywords = {Intrusion Detection System, Zero-Day Attacks, Artificial Intelligence, Machine Learning, Deep Learning, Enterprise Networks, Cybersecurity.},
month = {May},
doi = {https://doi.org/10.64388/IREV9I11-1718202}
}