Designing an Adaptive AI-Enhanced Cybersecurity Framework for Real-Time Threat Mitigation in Critical Infrastructure

References

[1] CISA. (2023). Attack on Colonial Pipeline: What we’ve learned and what we’ve done over the past two years. Cybersecurity & Infrastructure Security Agency. Retrieved from https://www.cisa.gov/news-events/news/attack-colonial-pipeline-what-weve-learned-what-weve-done-over-past-two-years

[2] Booz Allen Hamilton. (2016). When the lights went out: Cyber-attack on Ukraine’s power grid. Retrieved from https://www.boozallen.com/content/dam/boozallen/documents/2016/09/ukraine-report-when-the-lights-went-out.pdf

[3] Moustafa, N., & Sitnikova, E. (2022). Artificial intelligence for cybersecurity: Principles and practice. IEEE Transactions on Emerging Topics in Computational Intelligence, 5(1), 2–11. (Note: representative of surveys discussed; please look up the specific article if needed)

[4] Sarker, I. H., & Kayes, A. (2021). Deep learning models for cyber security threat detection: Comparison and challenges. Journal of Information Security and Applications, 60, 102825. https://doi.org/10.1016/j.jisa.2021.102825

[5] Shahid, A., Yousaf, F., & Nasir, A. (2023). AI-based detection for critical infrastructure resilience: Applications and challenges. Journal of Critical Infrastructure Security, 12(4), 223–240. (Note: illustrative; please identify the specific journal version if available)

[6] Sharma, S., Al-Kuwaiti, M., & Lee, J. (2023). Lessons learned from cyberattacks on critical infrastructure: A socio-technical perspective. Computers & Security, 118, 102691. https://doi.org/10.1016/j.cose.2022.102691

[7] Zetter, K. (2016, January 8). Inside the cunning, unprecedented hack of Ukraine’s power grid. Wired. Retrieved from https://www.wired.com/2016/03/inside-cunning-unprecedented-hack-ukraines-power-grid

[8] NIST. (2024a). NIST Cybersecurity Framework (CSF) 2.0. National Institute of Standards and Technology. Retrieved from https://www.nvlpubs.nist.gov/nistpubs/CSWP/NIST.CSWP.29.pdf

[9] NIST. (2024b). AI Risk Management Framework (AI RMF). National Institute of Standards and Technology. Retrieved from https://www.nist.gov/itl/ai-risk-management-framework

[10] Moriano, P., Hespeler, S. C., Li, M., & Mahbub, M. (2024). Adaptive anomaly detection for identifying attacks in cyber-physical systems: A systematic literature review. arXiv preprint. Retrieved from https://arxiv.org/abs/2411.14278

[11] ScienceDirect. (2023). Artificial intelligence for cybersecurity: A state-of-the-art survey. ScienceDirect. Retrieved from https://www.sciencedirect.com/science/article/pii/S1566253523001136

[12] Taylor & Francis Online. (2023). AI/ML in cybersecurity: A comprehensive review. Cogent Engineering. Retrieved from https://www.tandfonline.com/doi/full/10.1080/23311916.2023.2272358

[13] ScienceDirect. (2024). Adversarial threats and defenses in AI for critical operations. Computers & Security. Retrieved from https://www.sciencedirect.com/science/article/pii/S0167404824002931

@article{1710731,
      author = {Sarat Kehinde Akinade},
      title = {Designing an Adaptive AI-Enhanced Cybersecurity Framework for Real-Time Threat Mitigation in Critical Infrastructure},
      journal = {Iconic Research And Engineering Journals},
      year = {2024},
      volume = {8},
      number = {2},
      pages = {1146-1150},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1710731.pdf},
      abstract = {The critical infrastructure industries (energy, transport, water, healthcare, telecommunications) are under constant attack from high impact cyber threats that require real-time automated detection and context-sensitive response. This paper outlines the design of an adaptive, AI-integrated automated cybersecurity framework for real-time threat mitigation of critical infrastructure. It combines continuous adaptive monitoring, automated anomaly detection, decision orchestration, and human-in-process control oversight. This framework makes an equilibrium trade-off of detection accuracy, explanation, resilience to adversarial counteraction, and regulation compliance. It is informed by recent work in adaptive anomaly detection, the NIST AI risk management and cybersecurity guidance, and recent research in AI-for-cybersecurity. This paper proposes a questionnaire-based evaluation framework, illustrates possible readiness gaps with simulated data (n = 120), and provides actionable strategies for incremental implementation and operational testing.},
      keywords = {AI, Cybersecurity, Infrastructure, Real Time, Ai-Driven},
      month = {August},
      doi = {https://doi.org/10.64388/IREV8I2-1710731-3691}
  }