ADVANCED HYBRID MODEL WITH RISK-BASED AND COOPERATIVE CLOUD SECURITY STRATEGIES
DOI:
https://doi.org/10.28925/2663-4023.2025.29.970Keywords:
cloud computing, resource allocation, cybersecurity, game theory, cooperative games, coalition games, evolutionary optimization, NSGA-II, dynamic risk, multi-criteria optimization.Abstract
The article develops and theoretically justifies an extended hybrid model of cooperative-evolutionary distribution of tasks in cloud computing systems, taking into account the dynamic level of cyber risks and cooperative protection strategies. The proposed model integrates multi-criteria evolutionary optimization based on the modified NSGA-II algorithm with game-theoretic approaches, including cooperative, non-antagonistic and coalition games. For the first time, a dynamic risk function λ(t) is introduced, which varies in time according to stochastic, Markov or evolutionary models, which allows us to adequately reflect the adaptive nature of modern cyber threats and the dependence of risk on the state of the system, load, attack history and defender actions. A flexible adaptive defender strategy is developed, which responds in real time to the current level of risk by redistributing tasks, migrating to less vulnerable nodes, strengthening the protection of critical components and optimizing the use of security resources. In addition to the traditional optimization criteria – performance (execution time), cost and security level – the coalition benefit criterion was introduced for the first time as a separate optimization object, reflecting the synergistic effect of cooperation between different protective components or organizations in multi-cloud or distributed environments. Computer modeling was performed on synthetic data simulating real cloud infrastructure. A set of Pareto-optimal solutions was obtained in the four-dimensional space of objective functions. The quality of the resulting Pareto front was assessed using standard metrics. The results indicate a high diversification of solutions and effective reflection of trade-offs between conflicting criteria, and also confirm the possibility of achieving significant coalition benefit at the expense of a moderate increase in risk or cost. The proposed CoopEvo-CloudSec method demonstrates high adaptability to the changing risk profile of the cloud environment, ensuring a balance between productivity, cost-effectiveness, security and collective benefit from the cooperation of defenders. The model is described in the form of formalized mathematical expressions, pseudocode, and algorithm flowchart, which makes it suitable for further software implementation and practical application in real cloud infrastructures.
Downloads
References
Mykhailiv, V. I. (2015). Experimental Studies of Information Technology for Data Protection in Cloud Computing Systems. Current Problems of Automation and Information Technologies, 19, 52–66.
Tsyrkaniuk, D. (2025). A Model for the Distribution of Computational Tasks in Cloud Infrastructure Incorporating Performance, Cost, And Security Considerations. Cybersecurity Education Science Technique, 4(28), 619–632. https://doi.org/10.28925/2663-4023.2025.28.836
Qin, S., Pi, D., Shao, Z., & Xu, Y. (2023). A Cluster-based Cooperative Co-Evolutionary Algorithm for Multiobjective Workflow Scheduling in a Cloud Environment. IEEE Transactions on Automation Science and Engineering, 20(3), 1648–1662. https://doi.org/10.1109/tase.2022.3183681
Tan, B., H., Mei, Y., & Zhang, M. (2020). A Cooperative Coevolution Genetic Programming Hyper-Heuristics Approach for On-Line Resource Allocation in Container-Based Clouds. IEEE Transactions on Cloud Computing, 10(3), 1500–1514. https://doi.org/10.1109/tcc.2020.3026338
Goudarzi, S., Soleymani, S., Wang, W., & Xiao, P. (2023). UAV-Enabled Mobile Edge Computing for Resource Allocation Using Cooperative Evolutionary Computation. IEEE Transactions on Aerospace and Electronic Systems, 59, 5134–5147. https://doi.org/10.1109/taes.2023.3251967
Goudarzi, P., Hosseinpour, M., & Ahmadi, M. (2020). Joint Customer/Provider Evolutionary Multi-objective Utility Maximization in Cloud Data Center Networks. Iranian Journal of Science and Technology, Transactions of Electrical Engineering, 45(2), 479–492. https://doi.org/10.1007/s40998-020-00381-x
Guzek, M., Bouvry, P., & Talbi, E.-G. (2015). A Survey of Evolutionary Computation for Resource Management of Processing in Cloud Computing. IEEE Computational Intelligence Magazine, 10(2), 53–67. https://doi.org/10.1109/mci.2015.2405351
Atwal, S., Singh, D., & Chhabra, A. (2025). Resource Allocation Strategies for Edge and Fog Computing in the Cloud Continuum. In 2025 Int. Conf. on Intelligent Control, Computing and Communications (IC3), 208–213. https://doi.org/10.1109/ic363308.2025.10957263
Du, J., Jiang, C., Benslimane, A., Guo, S., & Ren, Y. (2021). SDN-based Resource Allocation in Edge and Cloud Computing Systems: An Evolutionary Stackelberg Differential Game Approach. IEEE/ACM Transactions on Networking, 30(4), 1613–1628. https://doi.org/10.1109/tnet.2022.3152150
Fan, W., Zhao, L., Liu, X., Su, Y., Li, S., Wu, F., & Liu, Y. (2024). Collaborative Service Placement, Task Scheduling, and Resource Allocation for Task Offloading With Edge-Cloud Cooperation. IEEE Transactions on Mobile Computing, 23(1), 238–256. https://doi.org/10.1109/tmc.2022.3219261
Choi, J., Choi, C., Lynn, H. M., & Kim, P. (2015). Ontology based APT Attack Behavior Analysis in Cloud Computing. In 2015 10th Int. Conf. on Broadband and Wireless Computing, Communication and Applications (BWCCA) (pp. 375–379). IEEE. https://doi.org/10.1109/bwcca.2015.69
Alshaikh, A., Alanesi, M., Yang, D., & Alshaikh, A. (2023). Advanced Techniques for Cyber Threat Intelligence-based APT Detection and Mitigation in Cloud Environments. In Int. Conf. on Cyber Security, Artificial Intelligence, and Digital Economy (CSAIDE 2023) (Vol. 12718, pp. 147–157). SPIE. https://doi.org/10.1117/12.2681627
Shabala, Y., & Korniichuk, B. (2024). Methodology for Assessing IoT Security at Industrial Facilities. Management of Development of Complex Systems, 60, 146–155. https://doi.org/10.32347/2412-9933.2024.60.146-155
Stefurak, O. R., Tykhonov, Yu. O., Laptyev, O. A., & Zozulya, S. A. (2020). Improving the Stochastic Model to Identify Threats of Damage or Unauthorized Leakage. Modern Information Security, 2, 19–26. https://doi.org/10.31673/2409-7292.2020.021926
Li, B., Chen, Y., Huang, S., Yao, R., Xia, Y., & Mei, S. (2019). Graphical Evolutionary Game Model of Virus-based Intrusion to Power System for Long-Term Cyber-Security Risk Evaluation. IEEE Access, 7, 178605–178617. https://doi.org/10.1109/access.2019.2958856
Zhang, H., Tan, J., Liu, X., Huang, S., Hu, H., & Zhang, Y. (2022). Cybersecurity Threat Assessment Integrating Qualitative Differential and Evolutionary Games. IEEE Transactions on Network and Service Management, 19(3), 3425–3437. https://doi.org/10.1109/tnsm.2022.3166348
Höfer, C. N., & Karagiannis, G. (2011). Cloud Computing Services: Taxonomy and Comparison. Journal of Internet Services and Applications, 2(2), 81–94. https://doi.org/10.1007/s13174-011-0027-x
Li, P., & Yang, X. (2019). On Dynamic Recovery of Cloud Storage System under Advanced Persistent Threats. IEEE Access, 7, 103556–103569. https://doi.org/10.1109/access.2019.2932020
Winter, E. (2002). Chapter 53 The shapley value. In Handbook of Game Theory with Economic Applications (pp. 2025–2054). Elsevier. https://doi.org/10.1016/s1574-0005(02)03016-3
Faigle, U., & Kern, W. (1992). The Shapley Value for Cooperative Games under Precedence Constraints. International Journal of Game Theory, 21, 249–266.
Golovanenko, M. (2012). Application of Cooperative Game Theory for the Development of Corporate Social Responsibility. Ukraine: Aspects of Labor, 2, 47–50.
Pavlov, I. M., & Tolyupa, S. V. (2014). Analysis of Approaches to Modeling Decision-making Processes in the Design of Information Security Systems. Modern Information Security, 2, 96–104.
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Діана Цирканюк
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
