Abstract

Conventional security systems that depend on static rules and signature-based detection are increasingly challenged by the sophistication of modern cyber threats. This study examines how machine learning and behavioral analytics can be combined to strengthen cyber threat detection in contemporary digital environments. A two-phase design is adopted: an analytical review of current machine learning algorithms, behavioral monitoring methods, and adaptive cybersecurity frameworks, followed by an empirical evaluation on the NSL-KDD benchmark using its official training and testing split. Five detection approaches are evaluated: Decision Tree, Random Forest, support vector machine (SVM), a multilayer perceptron neural network, and an Isolation Forest trained exclusively on normal traffic to emulate behavioral baseline profiling. The Decision Tree attains the highest test accuracy (81.4%, F1 = 0.811), while the Random Forest achieves the strongest ranking ability (AUC = 0.960); the behavioral Isolation Forest reaches 79.6% accuracy and an AUC of 0.946 without observing a single labeled attack, together with the lowest false-positive rate (2.35%). A feature-group ablation shows that behavioral traffic features raise the unsupervised detector's F1-score from 0.311 to 0.793 and that behavioral features alone support an AUC of approximately 0.90 across all model families. Detection of rare attack classes (R2L, U2R) remains weak across every model, quantifying the impact of class imbalance. Based on the combined analytical and experimental evidence, an integrated multi-layered framework is proposed that couples behavioral profiling with adaptive machine learning classification to support proactive, scalable cyber defense in enterprise and cloud environments.

References

• Kommera, H. K. R. 2024. Adaptive cybersecurity in the digital age: emerging threat vectors and next-generation defense strategies. International Journal for Research in Applied Science and Engineering Technology 12, 9, 558–564. DOI: 10.22214/ijraset.2024.64226.
• Afifi, H., Pochaba, S., Boltres, A., Laniewski, D., Haberer, J., Paeleke, L., et al. 2024. Machine learning with computer networks: techniques, datasets, and models. IEEE Access 12, 54673–54720. DOI: 10.1109/ACCESS.2024.3384460.
• Vemulapalli, V. K. 2025. AI-driven cybersecurity: the future of adaptive threat defense. World Journal of Advanced Research and Reviews 26, 2, 3248–3255. DOI: 10.30574/wjarr.2025.26.2.1953.
• Sultana, S., Uddin, M., Chy, M. A. R., Hasan, S. N., Hossain, E., Kaur, H., et al. 2025. AI-augmented big data analytics for real-time cyber attack detection and proactive threat mitigation. International Journal of Computational and Experimental Science and Engineering 11, 3. DOI: 10.22399/ijcesen.3564.
• Elbasi, E., Zaki, C., Topcu, A. E., Abdelbaki, W., Zreikat, A. I., Cina, E., et al. 2023. Crop prediction model using machine learning algorithms. Applied Sciences 13, 16, 9288. DOI: 10.3390/app13169288.
• Aminzadeh, A., Sattarpanah Karganroudi, S., Majidi, S., Dabompre, C., Azaiez, K., Mitride, C., and Sénéchal, E. 2025. A machine learning implementation to predictive maintenance and monitoring of industrial compressors. Sensors 25, 4, 1006. DOI: 10.3390/s25041006.
• Pelima, L. R., Sukmana, Y., and Rosmansyah, Y. 2024. Predicting university student graduation using academic performance and machine learning: a systematic literature review. IEEE Access 12, 23451–23465. DOI: 10.1109/ACCESS.2024.3361479.
• Swacha, J. and Gracel, M. 2023. Machine learning in gamification and gamification in machine learning: a systematic literature mapping. Applied Sciences 13, 20, 11427. DOI: 10.3390/app132011427.
• Hasan, S. N., Kaur, H., Mohonta, S. C., Siddiqa, K. B., Kaur, J., Haldar, U., et al. 2025. The influence of artificial intelligence on data system security. International Journal of Computational and Experimental Science and Engineering 11, 3. DOI: 10.22399/ijcesen.3476.
• Kolawole, I. 2025. Leveraging cloud-based AI and zero trust architecture to enhance U.S. cybersecurity and counteract foreign threats. World Journal of Advanced Research and Reviews 25, 3, 006–025. DOI: 10.30574/wjarr.2025.25.3.0635.
• Altalhan, M., Algarni, A., and Turki-Hadj Alouane, M. 2025. Imbalanced data problem in machine learning: a review. IEEE Access 13, 13686–13699. DOI: 10.1109/ACCESS.2025.3531662.
• Pinheiro, J. M. H., Oliveira, S. V. B. de, Silva, T. H. S., Saraiva, P. A. R., Souza, E. F. de, Godoy, R. V., et al. 2025. The impact of feature scaling in machine learning: effects on regression and classification tasks. IEEE Access 13, 199903–199931. DOI: 10.1109/ACCESS.2025.3635541.
• Rainio, O., Teuho, J., and Klén, R. 2024. Evaluation metrics and statistical tests for machine learning. Scientific Reports 14, 1, 6086. DOI: 10.1038/s41598-024-56706-x.
• Kreuzberger, D., Kühl, N., and Hirschl, S. 2023. Machine learning operations (MLOps): overview, definition, and architecture. IEEE Access 11, 31866–31879. DOI: 10.1109/ACCESS.2023.3262138.
• Reddy, K. V. S. P., Mohith, B., Babu, P. M., and Navtej, K. 2025. CyberSleuth AI: intelligent network forensics analyzer. International Journal for Research in Applied Science and Engineering Technology 13, 4, 1643–1647. DOI: 10.22214/ijraset.2025.68420.
• Chawande, S. 2024. The role of artificial intelligence in cybersecurity. World Journal of Advanced Engineering Technology and Sciences 11, 2, 683–696. DOI: 10.30574/wjaets.2024.11.2.0014.
• Ajayi, R. and Masunda, M. 2025. Integrating edge computing, data science and advanced cyber defense for autonomous threat mitigation. International Journal of Science and Research Archive 15, 2, 063–080. DOI: 10.30574/ijsra.2025.15.2.1292.
• Bansal, I. 2025. Implementing adaptive security monitoring: AWS CloudWatch and advanced threat detection techniques. International Journal of Computational and Experimental Science and Engineering 11, 3. DOI: 10.22399/ijcesen.3482.
• Palla, S. R. 2025. AI-driven fraud detection and security: a transformative approach for financial services cloud environments. World Journal of Advanced Research and Reviews 26, 1, 2040–2050. DOI: 10.30574/wjarr.2025.26.1.1296.
• Khattak, F. K., Subasri, V., Krishnan, A., Pou-Prom, C., Akinli-Kocak, S., Dolatabadi, E., et al. 2025. MLHOps: machine learning health operations. IEEE Access 13, 20374–20412. DOI: 10.1109/ACCESS.2024.3521279.
• Tavallaee, M., Bagheri, E., Lu, W., and Ghorbani, A. A. 2009. A detailed analysis of the KDD CUP 99 data set. In Proceedings of the 2009 IEEE Symposium on Computational Intelligence for Security and Defense Applications (CISDA), IEEE, 1–6. DOI: 10.1109/CISDA.2009.5356528.
• Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., et al. 2011. Scikit-learn: machine learning in Python. Journal of Machine Learning Research 12, 2825–2830.