International Journal of Computer Applications |
Foundation of Computer Science (FCS), NY, USA |
Volume 186 - Number 69 |
Year of Publication: 2025 |
Authors: Md. Aminur Rahman, Manjur Ahammed, Mohammad Mizanur Rahaman, Alvi Amin Khan |
![]() |
Md. Aminur Rahman, Manjur Ahammed, Mohammad Mizanur Rahaman, Alvi Amin Khan . AI-Driven Cybersecurity: Leveraging Machine Learning Algorithms for Advanced Threat Detection and Mitigation. International Journal of Computer Applications. 186, 69 ( Mar 2025), 50-60. DOI=10.5120/ijca2025924526
The rapid evolution of cyber threats necessitates advanced solutions, and Artificial Intelligence (AI) has emerged as a transformative tool in cybersecurity. This study aims to evaluate the effectiveness of AI-driven machine learning algorithms—Convolutional Neural Networks (CNN), Artificial Neural Networks (ANN), and Support Vector Machines (SVM)—in enhancing threat detection and mitigation. Leveraging the KDD Cup 99 dataset, the research employs a rigorous experimental setup, including data preprocessing, feature selection, and algorithm evaluation using accuracy, precision, recall, F1-score, and ROC-AUC metrics. The results reveal that CNN outperformed other models, achieving a 96.5% accuracy and demonstrating superior capability in identifying complex attack patterns. ANN and SVM also performed well, with accuracies of 94.8% and 92.1%, respectively. These findings underscore the potential of AI to bolster cybersecurity frameworks, offering improved detection rates and reduced false positives. The study contributes to the growing field of AI-driven cybersecurity by providing actionable insights for integrating machine learning models into practical applications. Future research is encouraged to explore hybrid models, real-time threat intelligence, and broader datasets to further enhance the adaptability and efficacy of AI-driven solutions in combating the dynamic landscape of cyber threats.