AI-Based Threat Monitoring Framework for Critical Infrastructure in Developing Economies

The increasing digitalization of critical infrastructure by developing countries has opened new security problems that existing conventional methods have failed to address. Particularly with advanced threats rapidly evolving. This paper aims to develop a system that monitors both active and passive threats using Artificial Intelligence integrated with lightweight deep learning for optimization to watch for threats in places where resources are limited. We used an hybrid model that combines Autoencoder and LSTM. The model performed excellently in learning threats. We used 20 epochs in training the system and observed a stable convergence when training the epochs and when it was tested, which means it performed good in terms of it generalization capacity. The reconstruction error distributions result showed a significant separation between benign and anomalous events (p < 0.01). Our tests showed that the proposed threat model framework was very good at detecting threats with accuracy of 96% and a confidence range of 94.95% to 97.05%. We did a a two-sample t-test comparing reconstruction errors between normal and attack traffic that produced a statistically significant separation (t ≈ 18.7, p < 0.001) with threat detection score of 95%. This showed the model performed well at telling the difference between attack traffic. All these results together show that our model is reliable and can work well in places where resources are limited. The outcome is a system that can watch for threats and adapt to situations, within countries that are resource constrained.

Artificial Intelligence, Threat Monitoring

1. Ahmed, M., Mahmood, A. N., & Hu, J. (2016). 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 [Google Scholar] [Crossref]

2. Aldweesh, A., Derhab, A., & Emam, A. Z. (2020). Deep learning approaches for anomaly-based intrusion detection systems: A survey, taxonomy, and open issues. Knowledge-Based Systems, 189, 105124. https://doi.org/10.1016/j.knosys.2019.105124 [Google Scholar] [Crossref]

3. Alrashdi, I., Alqazzaz, A., Aloufi, E., Alharthi, R., Zohdy, M., & Ming, H. (2020). An intrusion detection system for IoT based on machine learning: A comparative study. Electronics, 9(4), 1–23. https://doi.org/10.3390/electronics9040649 [Google Scholar] [Crossref]

4. Amin, R., Islam, S. H., & Biswas, G. (2021). Machine learning for cybersecurity in developing nations: Challenges and opportunities. Computers & Security, 103, 102209. https://doi.org/10.1016/j.cose.2020.102209 [Google Scholar] [Crossref]

5. Ani, U. D., He, H., & Tiwari, A. (2023). Socio-technical security modelling: A systematic analysis of the state of the art. Computers & Security, 126, Article 103059. https://doi.org/10.1016/j.cose.2022.103059 [Google Scholar] [Crossref]

6. Estay, D. A. S., Muñoz, P., & Rivera, D. E. (2020). A systematic review of cyber-resilience assessment frameworks. Computers & Security, 95, 101855. https://doi.org/10.1016/j.cose.2020.101855 [Google Scholar] [Crossref]

7. Husák, M., Laštovička, M., & Čermák, M. (2022). CRUSOE: A toolset for cyber situational awareness and decision support. Computers & Security, 113, 102546. https://doi.org/10.1016/j.cose.2021.102546 [Google Scholar] [Crossref]

8. Kim, D., Lee, J., & Park, J. H. (2022). A CNN-LSTM hybrid model for network intrusion detection. IEEE Access, 10, 12290–12305. https://doi.org/10.1109/ACCESS.2022.3142364 [Google Scholar] [Crossref]

9. Lin, C., Yang, L., & Li, Z. (2021). Lightweight deep learning framework for real-time anomaly detection in industrial IoT. IEEE Access, 9, 12345–12358. https://doi.org/10.1109/ACCESS.2021.3053909 [Google Scholar] [Crossref]

10. Madan, S., & Bedi, P. (2022). Artificial intelligence–based security for critical infrastructure: Challenges and opportunities. Computers & Security, 117, Article 102719. https://doi.org/10.1016/j.cose.2022.102719 [Google Scholar] [Crossref]

11. Ogundokun, R. O., Akande, S. O., & Salawu, S. A. (2023). AI-driven cybersecurity for developing nations: A survey of adaptive methods. ICTACT Journal on Soft Computing, 13(4), 290–299. https://doi.org/10.21917/ijsc.2023.0405 [Google Scholar] [Crossref]

12. Zhang, Y., & Xu, C. (2022). Federated learning for cyber threat intelligence sharing. IEEE Transactions on Information Forensics and Security, 17, 3152–3163. https://doi.org/10.1109/TIFS.2022.3180035 [Google Scholar] [Crossref]

13. Zhao, X., Xu, F., & Wang, J. (2022). Anomaly detection approach in industrial control systems. Information, 13(10), 450. https://doi.org/10.3390/info13100450 [Google Scholar] [Crossref]

• Impact of Foreign Direct Investment in India
• Issues Involved in Digitalisation Special Reference to Indian Tourism Growth
• Relationship Marketing and Customer Loyalty in the Fast-Moving Consumer Goods (FMCG) Industry in Nairobi County
• Financial Literacy or Financial Inclusion? Which is Which, What is What—To Achieve Uganda’s 10-Fold Economic Growth By 2040
• Harnessing Natural Gas for Economic Transformation: Overcoming the Regulatory and Infrastructural Bottlenecks in Nigeria