Abstract—The evolution of cyber threats has imposed the need for robust Intrusion Detection Systems (IDSs) that are capable of detecting intrusions with high accuracy. This paper proposes an IDS based on Machine Learning (ML), which uses a modified African Vultures Optimization Algorithm (AVOA) for Feature Selection (FS). The AVOA was enhanced using a crossover function. The crossover was implemented to enhance the algorithm’s ability to explore the FS solution space. The proposed model was further evaluated on the UNSW-NB15 dataset with binary classification. Binary classification showed an excellent performance using the XGBoost and Hist Gradient Boosting classifiers, with an accuracy and a precision of 99.77%. These results further indicate the efficiency of using AVOA for intrusion detection. This study depicts the potential of ML in the development of accurate and robust IDS solutions, thus setting a benchmark for future research in cybersecurity.

Keywords—Machine Learning (ML), Feature Selection (FS), Intrusion Detection System (IDS), African Vultures Algorithm (AVOA)



Cite: Yasameen A. Al-Shadeedi, Mosleh Abualhaj, Ahmad Abu-Shareha, Mohamed Yousif, and Anusha Achuthan, “Improved Intrusion Detection System Using a Modified African Vultures Alg," Journal of Communications, vol. 21, no. 2, pp. 284-293, 2026.

Copyright © 2026 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).