Media of University of Babylon | Distinguished Research Publication by a Faculty Member from the Department of Information Networks on Enhancing IoT Security

Media of University of Babylon - كلية الطب

Distinguished Research Publication by a Faculty Member from the Department of Information Networks on Enhancing IoT Security

by : Duhaa Fadill Abbas

Date : 15/7/2025 08:02:07 PM

Veiw : 35

Distinguished Research Publication by a Faculty Member from the Department of Information Networks on Enhancing IoT Security Using Intelligent Algorithms and Hybrid Deep Learning Models

Duhaa Fadill Abbas
In alignment with the strategic vision of the Department of Information Networks at the College of Information Technology, University of Babylon, aimed at fostering scientific research in cybersecurity and artificial intelligence, Assistant Lecturer Taif Alaa Al-Ameedi, a faculty member in the department, in collaboration with a distinguished group of researchers from Universiti Sains Malaysia, Taibah University in Saudi Arabia, and Tanta University in Egypt, has published a high-impact scientific paper titled:
“A Framework for Botnet Attack Detection in the Internet of Things Based on Bio-Inspired Multi-Feature Selection and Hybrid Deep Learning Model”

The research was published in the Alexandria Engineering Journal, a prestigious journal issued by Elsevier, indexed in Clarivate’s Q1 quartile, and boasting an impressive impact factor of 6.8, reflecting the paper’s academic quality and scientific significance.

The study addresses one of the most pressing cybersecurity challenges in the digital era—botnet attacks targeting Internet of Things (IoT) environments. The proposed paper introduces an innovative intelligent intrusion detection system named Bot-EnsIDS, which integrates nature-inspired optimization algorithms such as Particle Swarm Optimization (PSO) and Gorilla Troops Optimizer (GTO) with a hybrid deep learning model that combines Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks.

This system stands out for its ability to efficiently handle high-dimensional IoT traffic data and accurately detect emerging or obfuscated cyberattacks. It further leverages Generative Adversarial Networks (GAN) for automatic data augmentation, enhancing the model’s robustness and adaptability.

Experimental evaluations using the benchmark BoT-IoT dataset demonstrated outstanding results:

- Detection accuracy of 97%
- Recall and precision of 97.5%
- F-Measure of 97.5%
- False Positive Rate as low as 0.025

These results indicate the system’s exceptional performance in accurately distinguishing between normal and malicious traffic, while minimizing false alarms, thereby offering a promising and scalable solution for real-world IoT security applications.

The research team included the following collaborators:

- Ms. Tamara Al-Sharbaji – Universiti Sains Malaysia
- Prof. Dr. Mohamed Anbar – Universiti Sains Malaysia
- Prof. Dr. Selvakumar Manickam – Universiti Sains Malaysia
- Ms. Ghada Al-Mukhaini – Universiti Sains Malaysia
- Dr. Hassan Hashem – Taibah University, Saudi Arabia
- Dr. Mohammed Farsi – Taibah University, Saudi Arabia
- Prof. Dr. Sayed Atlam – Tanta University, Egypt

This scientific achievement represents a valuable contribution to the College of Information Technology’s growing portfolio of applied research and highlights the fruitful international academic collaboration of its faculty with globally recognized institutions.

?? Link to the full paper:
https://www.sciencedirect.com/science/article/pii/S1110016825007707