NORMA eResearch @NCI Library

Network Intrusion Detection System using CNN-LSTM Hybrid Network

Kokkali, Ajeeser (2022) Network Intrusion Detection System using CNN-LSTM Hybrid Network. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
PDF (Master of Science)
Download (890kB) | Preview
[thumbnail of Configuration manual]
PDF (Configuration manual)
Download (624kB) | Preview


Most service providers are concerned about the rise in computer networks and internet assaults. It has prompted the development and use of intrusion detection systems (IDSs) to aid in the prevention or mitigation of network intruder threats. Intrusion detection systems have played and continue to play a critical role in detecting network attacks and anomalies over the years. Many IDSs have been proposed by researchers all around the world to address the threat of network intruders. Most of the previously proposed IDSs, on the other hand, have a high proportion of false alarms. This research introduces a novel approach for enhanced intrusion detection that uses a hybrid algorithm of Convolutional Neural Network (CNN) and Long Short Term Memory (LSTM). NSL-KDD, a credible intrusion detection dataset that covers all typical, updated intrusions and cyberattacks, is used to evaluate DL-IDS. This bidirectional approach demonstrated the accuracy of 98.39 percent. Precision, false positive, F1 score, and recall were used to evaluate the algorithm's performance, and it was determined to be promising for deployment on live network infrastructure.

Item Type: Thesis (Masters)
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
Q Science > QA Mathematics > Computer software > Computer Security
T Technology > T Technology (General) > Information Technology > Computer software > Computer Security
Divisions: School of Computing > Master of Science in Cyber Security
Depositing User: Tamara Malone
Date Deposited: 19 Dec 2022 17:46
Last Modified: 19 Dec 2022 17:46

Actions (login required)

View Item View Item