Oct 2026· Journal of Computer Science and Technology Application· 0 citations· 56 references
TL;DR
A deep learning-based intrusion detection system for smart campus networks, utilizing a Hybrid CNN-LSTM model to enhance security monitoring and suggest that deep learning models, especially when tailored to smart campus contexts, offer significant advantages in real-time threat detection and adaptive learning.
Abstract
The increasing complexity of smart campus networks has heightened the need for advanced cybersecurity measures to protect sensitive data and ensure seamless operations. Traditional Intrusion Detection Systems (IDS) often struggle to cope with the dynamic and heterogeneous nature of network traffic in smart campus environments, necessitating the development of more effective solutions. This study aims to propose a deep learning-based intrusion detection system for smart campus networks, utilizing a Hybrid CNN-LSTM model to enhance security monitoring. The proposed methodology integrates Convolutional Neural Networks (CNN) for feature extraction and Long Short-Term Memory (LSTM) networks for capturing temporal dependencies in network traffic. The model was trained and evaluated on a combination of publicly available datasets and simulated smart campus data, measuring performance through key metrics such as accuracy, precision, recall, and F1-score. Results show that the Hybrid CNN-LSTM model outperforms traditional machine learning models, achieving an accuracy of 97.3% and a ROC-AUC of 0.99, demonstrating superior detection of both known and unknown intrusions. The findings suggest that deep learning models, especially when tailored to smart campus contexts, offer significant advantages in real-time threat detection and adaptive learning. This research contributes to the growing body of knowledge on AI-driven network security and provides practical insights for improving cybersecurity infrastructures in higher education institutions.
The growing complexity of cyber threats has made it essential to develop dependable network intrusion detection systems that can accurately identify both normal and harmful network traffic. This paper introduces an offline dataset-based Network Intrusion Detection and Prevention System (NIDS) built on a hybrid Convolut...
Nitin Dhamdhar, Chhatradip Hatwar, Chitransh Dalne et al.· International Journal for Re...· 0 citations
The rapid proliferation of the Industrial Internet of Things (IIoT) has significantly expanded the cyberattack surface of connected industrial systems, creating an urgent need for intelligent, reliable intrusion detection mechanisms to safeguard edge computing environments. This paper proposes a deep learning-based Int...
Hala Hayajneh, Qasem Abu Al-haija· Revolutionary Advances in Co...· 0 citations
A hybrid deep learning classification model (DNN-LSTM), applied to the Multi-Step Cyber–Attack Dataset (MSCAD), which consists of 66 features, highlights the superiority of the DNN-LSTM hybrid model in identifying multi-step cyberattacks, reducing false positives, and enhancing the overall efficiency of intrusion detec...
Dalia Kefah Neamet, Mahmood Zaki Abdullah· Journal of Applied Research...· 0 citations
A hybrid deep learning intrusion detection framework is presented to address the challenges of fast-evolving and heterogeneous nature of IoT traffic and achieves higher accuracy, precision, recall, and F1-score when compared with traditional machine learning approaches.
F. C. Uzoezie· International Journal of Com...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.