An Empirical Study of Attack Detection and Mitigation Using the TON_IoT Dataset | IJCT Volume 12 – Issue 6 | IJCT-V12I6P66
International Journal of Computer Techniques
ISSN 2394-2231
Author
Solanke Oluwole, Anyaehie Amarachi A., Ajayi Oluwabukola, Udosen Alfred
Abstract
The rapid proliferation of cyber threats targeting enterprise and Internet of Things (IoT) environments has heightened the demand for robust and experimentally validated network security solutions. Experimental network security research enables systematic evaluation of intrusion detection mechanisms under controlled and reproducible conditions. This paper presents a comprehensive experimental study of network attack detection and mitigation using the TON_IoT dataset, a modern benchmark that captures realistic network traffic, system telemetry, and attack behaviors in IoT-enabled infrastructures. Signature-based, anomaly-based, and hybrid intrusion detection approaches are experimentally evaluated across multiple attack categories, including denial-of-service, scanning, malware injection, and privilege escalation. Mathematical models are formulated for feature normalization, classification, and performance evaluation. Experimental results demonstrate that the hybrid detection model achieves superior accuracy, precision, recall, and F1-score while maintaining acceptable latency and throughput overhead. The findings provide empirical evidence supporting hybrid intrusion detection strategies for securing contemporary networked and IoT systems.
Keywords
Experimental network security, intrusion detection systems, TON_IoT dataset, hybrid detection, IoT security
Conclusion
This paper presented a comprehensive experimental study of network attack detection using the TON_IoT dataset. Through mathematical modeling and empirical evaluation, the study demonstrated that hybrid intrusion detection mechanisms provide superior accuracy and robustness while maintaining operational feasibility. Future work will explore deep learning-based detection, real-time adaptive models, and large-scale distributed testbeds to further enhance experimental network security research.
References
Moustafa, N., Turnbull, B., & Choo, K. K. R. (2021). TON_IoT datasets: A new generation of realistic IoT and IIoT datasets for cybersecurity research. IEEE Access, 9, 76321–76344.
Sommer, R., & Paxson, V. (2010). Outside the closed world: On using machine learning for network intrusion detection. IEEE Symposium on Security and Privacy, 305–316.
Lippmann, R., et al. (2000). Evaluating intrusion detection systems: The 1998 DARPA off-line intrusion detection evaluation. DARPA Information Survivability Conference and Exposition.
Buczak, A. L., & Guven, E. (2016). A survey of data mining and machine learning methods for cyber security intrusion detection. IEEE Communications Surveys & Tutorials, 18(2), 1153–1176.
Chandola, V., Banerjee, A., & Kumar, V. (2009). Anomaly detection: A survey. ACM Computing Surveys, 41(3), 1–58.
Sharafaldin, I., Lashkari, A. H., & Ghorbani, A. A. (2018). Toward generating a new intrusion detection dataset and intrusion traffic characterization. ICISSP, 108–116.
Moustafa, N., & Slay, J. (2016). UNSW-NB15: A comprehensive data set for network intrusion detection systems. Military Communications and Information Systems Conference.
Mishra, P., Varadharajan, V., Tupakula, U., & Pilli, E. S. (2018). A detailed investigation and analysis of using machine learning techniques for intrusion detection. IEEE Communications Surveys & Tutorials, 21(1), 686–728.
How to Cite This Paper
Solanke Oluwole, Anyaehie Amarachi A., Ajayi Oluwabukola, Udosen Alfred (2025). An Empirical Study of Attack Detection and Mitigation Using the TON_IoT Dataset. International Journal of Computer Techniques, 12(6). ISSN: 2394-2231.
Related Posts:
