Abstract :

The Rapid Proliferation Of The Internet Of Things (IoT) Has Led To An Increased Vulnerability To Botnet Attacks, Posing Significant Challenges To Network Security. Traditional Detection Methods Often Fall Short In Effectively Identifying And Mitigating These Threats Due To The Dynamic Nature Of IoT Environments. Thisproject Proposes A Hybrid Machine Learning Model (ACLR) That Combines The Strengths Of Artificial Neural Networks (ANN), Convolutional Neural Networks (CNN), Long Short-Term Memory Networks (LSTM), And Recurrent Neural Networks (RNN) To Efficiently Detect Botnet Attacks In IoT Networks.The Proposed Model Leverages A Stacking Ensemble Technique To Improve Accuracy And Reduce False Positives. Using The UNSW-NB15 Dataset, Which Includes Diverse Attack Categories Such As DDoS, Reconnaissance, And Worms, The Model Demonstrates Superior Performance Compared To Individual Deep Learning Models. With An Accuracy Of 0.9698 And A Receiver Operating Characteristic Area Underthe Curve (ROC-AUC) Score Of 0.9934, The ACLR Model Effectively Captures Complex Patterns In Network Traffic Data.This Research Contributes To The Development Of Robust And Scalable Botnetdetection Frameworks, Enhancing IoT Security And Enabling Proactive Threat Mitigation Strategies. The Findings Underline The Potential Of Hybrid Machine Learning Approaches To Address Evolving Cybersecurity Challenges In IoT Ecosystems. Index Terms — Internet Of Things (IoT), Long Short-Term Memory (LSTM), Recurrent Neural Network (RNN), Stacking Ensemble, Deep Learning, Cybersecurity, UNSW-NB15 Dataset.

Published:

29-10-2025

Issue:

Vol. 25 No. 10 (2025)

Page Nos:

388-397

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite