AI-POWERED SECURITY STRATEGIES FOR THE OSI MODEL

Yohannes Tadesse

doi:10.29121/shodhai.v3.i1.2026.62

Authors

Yohannes Tadesse Adjunct Professor, College of Business and Management, Metro State University, Saint Paul, (Minnesota), USA

DOI:

https://doi.org/10.29121/shodhai.v3.i1.2026.62

Keywords:

Artificial Intelligence (AI), OSI Model, Network Security, Machine Learning (ML), Deep Learning (DL), Anomaly Detection, Intrusion Detection, Malware Classification, Phishing Detection, Cybersecurity, Threat Prevention, Adaptive Security, Vulnerability Assessment, Real-Time Threat Response

Abstract

The rapid evolution of cyber threats has highlighted the limitations of conventional network security measures, underscoring the need for innovative, adaptive solutions. This study investigates the possibilities of artificial intelligence (AI)-driven security approaches to improve network security at every layer of the Open Systems Interconnection (OSI) model. By leveraging machine learning (ML), deep learning (DL), and natural language processing (NLP), the study introduces a cohesive framework for applying AI methods to address vulnerabilities at each OSI model layer. The study explored publicly available datasets, including CICIDS2017 and EMBER, in conjunction with real-world network data to train and evaluate AI models for various tasks, including anomaly detection, intrusion detection, malware classification, and phishing detection. The results demonstrate significant improvements over traditional security approaches, with AI-powered models achieving 90-97% accuracy in anomaly detection, 90-94% F1-score in intrusion detection with the Random Forest model, and 95-99% accuracy in malware classification. The study underscores AI's capability to analyze intricate patterns, adapt to emerging threats, and deliver immediate threat detection and response. Nonetheless, issues regarding data quality, computational complexity, and adversarial attacks have been identified as critical areas for further investigation. The results highlight the need for a comprehensive, flexible network security strategy that leverages AI to address connections across the OSI layers. This study adds to the growing body of knowledge on AI-powered cybersecurity and offers practical guidance for organizations seeking to enhance their security footprint in an increasingly connected environment.

References

Academy, E. (2024). Introduction to the OSI Model. EITCA Academy.

Ahmed, M., Mahmood, A. N., and Hu, J. (2015). A Survey of Network Anomaly Detection Techniques. Journal of Network and Computer Applications, 60, 19–31. https://doi.org/10.1016/j.jnca.2015.11.016

Al-Garadi, M. A., Mohamed, A., Al-Ali, A. K., Du, X., and Guizani, M. (2020). A Survey of Machine and Deep Learning Methods for Internet of Things (IoT) security. IEEE Communications Surveys & Tutorials, 22(3), 1646–1685.

Anderson, H. S., and Roth, P. (2018). EMBER: An Open Dataset for Training Static PE Malware Machine Learning Models (arXiv:1804.04637). arXiv. https://arxiv.org/abs/1804.04637

Buczak, A. L., and Guven, E. (2016). A Survey of Data Mining and Machine Learning Methods for Cybersecurity Intrusion Detection. IEEE Communications Surveys & Tutorials, 18(2), 1153–1176.

Christodorescu, M., and Jha, S. (2003). Static Analysis for Detecting Malicious Patterns. In Proceedings of the 17th USENIX Security Symposium 17, (169–184).

Cloppert, M. C., Hutchins, E. M., and Riden, T. L. (2013). Defining Operational Cyber Threat Intelligence. In 2013 8th International Conference on System of Systems Engineering (SoSE) (282–287).

Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep learning MIT Press.

Hnatiuk, I. (2024). SAAS Technology Stack: Everything Business Needs for Success. Blackthorn Vision.

Kaspersky. (2023). Advanced Persistent Threats: What you Need to Know.

Kreutz, D., Ramos, F. M. V., Verissimo, P. E., Rothenberg, C. E., Azodolmolky, S., and Uhlig, S. (2015). Software-Defined Networking: A Comprehensive Survey. Proceedings of the IEEE, 103(1), 14–76.

Li, Y., Sun, A., and Liu, A. (2018). Building a Phishing Email Detection System Based on Natural Language Processing. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing: System Demonstrations (55–60).

Liao, H. J., Lin, C. H. R., and Lin, Y. F. (2016). Intrusion Detection System: A Comprehensive Review. Journal of Network and Computer Applications, 76, 16–24.

Liu, F. T., Ting, K. M., and Zhou, Z. H. (2008). Isolation Forest. IEEE Conference Publication.

Lopez-Martin, M., Garcia, S., De Andres-Perez, A., and Perez-Gonzalez, J. L. (2017). Deep Learning for Network Traffic Classification in SDN and NFV.

MITRE. (2023). MITRE ATT&CK Framework.

Mishra, P. K., Varadharajan, V., Tupakula, U., and Pilli, E. S. (2019). A Detailed Analysis of the Recent Developments in Intrusion Detection Techniques. IEEE Communications Surveys & Tutorials, 21(1), 355–379.

Mohammed, N., Al-Mhiqani, M. N., and Ahmad, R. (2021). Artificial Intelligence in Cybersecurity: A Comprehensive Review. Journal of Network and Computer Applications, 185, 103–120.

Neuhaus, S., Zimmermann, T., Holler, A., and Zeller, A. (2007). Mining Revision History for Semantic Bug Report Classification. ACM Transactions on Information and System Security, 10(4), 1–28.

Panda, M., Abraham, A., and Patra, M. R. (2018). Hybrid Intelligent Approach for Network Intrusion Detection. Journal of Network and Computer Applications, 102, 47–59.

Pascanu, R., Stokes, J. W., Sanossian, H., Marinescu, A., and Thomas, S. (2015). MalNet: A Large-Scale Network of Malware Families. In International Conference on Machine Learning (1804–1813). PMLR.

Pittman, J. M., and Alaee, S. (2023). To what Extent are Honeypots and Honeynets Autonomic Computing Systems? https://arxiv.org/abs/2307.11038

Rieck, K., Holz, T., Willems, C., and Düssel, P. (2011). Learning and Classification of Malware Behavior. In Detection of Intrusions and Malware, and Vulnerability Assessment (107–126). Springer.

Roman, R., Zhou, J., and Lopez, C. (2018). Securing the Internet of Things: Vulnerabilities and challenges. IEEE Transactions on Network and Service Management, 15(3), 1054–1068.

Rootstack. (n.d.). Using AI and ML to Improve Software Security.

Samajdar, S. S., Chatterjee, R., Mukherjee, S., Dey, A., Saboo, B., Pal, J., Joshi, S., and Chatterjee, N. (2025). Artificial Intelligence in Healthcare: Current Trends and Future Directions. Current Medical Issues, 23(1), 53–60. https://doi.org/10.4103/cmi.cmi_93_24

Sarker, I. H., Kayes, A. S. M., Badsha, S., Alqahtani, H., Watters, P., and Ng, A. (2020). Cybersecurity Data Science: An Overview from Machine Learning perspective. Journal of King Saud University – Computer and Information Sciences, 32(7), 789–816.

Saxe, J., and Berlin, K. (2015). Deep Neural Network-Based Malware Detection using Two-Dimensional Binary Program Features. IEEE Conference Publication.

Sharafaldin, I., Lashkari, A. H., and Ghorbani, A. A. (2018). Toward Generating a New Intrusion Detection Dataset and Intrusion Traffic Characterization. In International Conference on Information Systems Security and Privacy (ICISSP).

Shaukat, K., Luo, S., Varadharajan, V., Liu, C., and Chen, S. (2020). A Survey on Machine Learning Techniques for Malware Analysis. EURASIP Journal on Information Security, 2020(1), 1–35.

Stallings, W. (2017). Network Security Essentials: Applications and Standards.

Symantec. (2022). The Evolution of Malware: From Viruses to Zero-Day Exploits.

Yadav, T., and Rao, A. M. (2015). Technical Aspects of Cyber Kill Chain. In International Symposium on Security in Computing and Communication (438–452). Springer.

Zetter, K. (2014). Countdown to Zero Day: Stuxnet and the Launch of the world’s First Digital Weapon. Crown.

Zhou, Y., Han, Q., and Liu, C. (2020). Anomaly Detection of Network Traffic Based on Deep Learning. IEEE Access, 8, 208221–208234.