Artificial Intelligence based Intrusion Detection System

Muhammad Moosa Bin Naseem; Sana Alam; Muhammad Abbas; Asghar Khan; Asim Ifthikhar; Wazir Ali; Qurrat-ul-Ain Naiyar

No Detail Found!

Artificial Intelligence based Intrusion Detection System

Author(s)

Muhammad Moosa Bin Naseem College of Computer Science and Information Systems, IoBM, Karachi Country: Pakistan

Sana Alam College of Computer Science and Information Systems, IoBM, Karachi Country: Pakistan

Muhammad Abbas College of Computer Science and Information Systems, IoBM, Karachi Country, Pakistan

Asghar Khan College of Computer Science and Information Systems, IoBM, Karachi Country, Pakistan

Asim Ifthikhar College of Computer Science and Information Systems, IoBM, Karachi Country, Pakistan

Wazir Ali College of Computer Science and Information Systems, IoBM, Karachi Country, Pakistan

Qurrat-ul-Ain Naiyar College of Computer Science and Information Systems, IoBM, Karachi Country, Pakistan

Abstract

One of the major aspects in today's digital world is to ensure network security. Traditional Intrusion Detection Systems (IDS) mainly focus on the identification and categorization of active attacks, often leaving networks vulnerable to passive and emerging threats. This article presents an advanced IDS that uses deep learning, specifically stacked Long Short-Term Memory (LSTM) and the CatBoost algorithm, to detect anomalies in network traffic. The proposed system is designed to flag suspicious IP addresses in a proactive manner to detect potential passive attacks before escalation. We train the IDS on LUFLow's 2021 dataset using the LSTM neural network with the agility of CatBoost. The proposed model yields an Area Under the Curve (AUC) score of 87%, which shows its performance in detecting normal and anomalous traffic. The proposed IDS has the capability to monitor and detect the cyber threats in real-time.

Publication Details

Page(s) 9-15

DOI DOI not available

Published Journal: Journal of Information & Communication Technology (JICT), Volume: 18, Issue: 2, Year: 2024

Request the full text from PASTIC

Keywords

Classification, Artificial Intelligence, Anomaly detection., CatBoost, intrusion detection systems, LSTM-AutoEncoder

References

Laghrissi S.,Douzi K.,Douzi B.,Hssina B.,Liu Y.,Li Z.,Pan S.,Gong C.,Zhou C.,Karypis G. .2021 .Anomaly detection on attributed networks via contrastiveselfsupervised learning. IEEE transactions on neural networks and learning systems, 33(6) : 2378-2392.

Hussain S.,Mustafa M.W.,Jumani T.A.,Baloch S.K.,Alotaibi H.,Khan I.,Khan A. .2021 .A novel feature engineered-CatBoost-based supervised machine learning framework for electricity theft detection. Energy Reports, 7 : 4425-4436.

Shahriar Al,Dey M.,A. M.,December. M. .2023 .A Hybrid Approach of CNN and LSTM to Detect Intrusion in Edge IoT Devices using CatBoost. In 2023 26th International Conference on Computer and Information Technology (ICCIT), : 1-6.

Hnamte V.,Nhung-Nguyen H.,Hussain J.,Hwa-Kim Y. .2023 .A novel two-stage deep learning model for network intrusion detection: LSTM-AE. , 11 : 37131-37148.

Elsayed Said,Le-Khac M.,Dev N.A.,Jurcut S.,A.D. S. .2020 .Network anomaly detection using LSTM based autoencoder. In Proceedings of the 16th ACM Symposium on QoS and Security for Wireless and Mobile Networks, : 37-45.

Long G.,Zhang Z. .2024 .PUNet: A SemiSupervised Anomaly Detection Model for Network Anomaly Detection Based on Positive Unlabeled Data. , 81(1) : .

Citations

Downloads

Views