Data-Driven Risk Management in Cybersecurity Using AI-Enhanced Bayesian Inference Models
Keywords:
Data-Driven Risk Management, Cybersecurity, AI, Bayesian Inference, Machine Learning, Predictive Analytics, Threat Detection, Probabilistic Modeling, Risk Mitigation, Decision Support SystemsAbstract
Cybersecurity threats have become increasingly sophisticated, making traditional risk management approaches less effective. This paper explores the integration of AI-enhanced Bayesian inference models into data-driven risk management strategies for cybersecurity. Bayesian inference offers a probabilistic framework that can incorporate prior knowledge and observed data to make predictions about potential risks in cybersecurity systems. By combining machine learning techniques with Bayesian methods, organizations can enhance their ability to assess and mitigate cybersecurity threats. The research discusses the theoretical foundations of Bayesian inference, its application in cybersecurity risk management, and the benefits of utilizing data-driven models to predict, detect, and respond to emerging threats. Additionally, the paper highlights case studies where AI-enhanced Bayesian models have been successfully employed in cybersecurity, showing how these methods can improve decision-making, reduce vulnerabilities, and strengthen overall system security.
Downloads
References
Agerri, R., & Garcia-Sanchez, P. (2019). Artificial intelligence for cybersecurity: A survey of techniques, tools, and applications. Artificial Intelligence Review, 52(2), 123-141.
Mohammed, Hameed Ul Hassan. "Machine Learning-Based Test Access Pattern Optimization for Minimizing Test Cost in SoC Design." (2022).
Mohamed, Thasil, et al. "Explainable Reinforcement Learning for Credit Underwriting and Clinical Trial Funding Decisions." Journal of Artificial Intelligence & Machine Learning Studies 2 (2018): 1-32.
Mohammed, Hameed Ul Hassan, and Deng Ying. "Performance-Driven Design Space Exploration Of Chip Multiprocessors Using Meta-Learning Techniques." Webology (ISSN: 1735-188X) 20.3 (2023).
Mohammed, Hameed Ul Hassan. "A Machine Learning-Driven Placement Optimization Framework for VLSI Physical Design." Journal of Computational Analysis and Applications 31.4 (2023).
Albrecht, A., & Wright, P. (2021). Machine learning for cybersecurity: A critical survey. Journal of Computer Science and Technology, 36(3), 47-62.
Bishop, C. M. (2006). Pattern recognition and machine learning. Springer.
Bontempi, G., & Vitiello, G. (2018). Using Bayesian networks for cybersecurity risk assessment. Journal of Risk Research, 21(4), 503-515.
Dubois, D., & Prade, H. (2017). Probability and uncertainty: A philosophical introduction. Routledge.
He, X., & Zhang, Z. (2020). Bayesian models for anomaly detection in cybersecurity. Security and Privacy, 4(2), 10-19.
Liao, H. F., & Wei, W. X. (2022). Advancements in AI-based cybersecurity. International Journal of Computer Applications, 35(1), 22-29.
Singh, S., & Kumar, P. (2019). Fraud detection in financial transactions using Bayesian models. Journal of Financial Technology, 27(3), 208-216.
Zhang, Y., & Wang, X. (2019). Data breach prediction and prevention using Bayesian networks in healthcare. International Journal of Health Information Systems, 34(5), 211-219.
Zhao, Q., & Xie, J. (2021). AI in cybersecurity: Case studies and future perspectives. Cybersecurity Journal, 12(1), 10-22.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Content published in the Journal of Artificial Intelligence for Data-Driven Discovery (JAIDDD) is licensed under the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License (CC BY-NC-SA 4.0). This license allows users to share and adapt the material, provided they:
-
Give appropriate credit to the original author(s).
-
Use the material for non-commercial purposes only.
-
Distribute any adaptations under the same license.
For permissions beyond this license, contact editor@jaiddd.org. Authors retain copyright and grant JAIDDD the right to publish and distribute their work.
