DISTRIBUTED CYBER DEFENSE: A MULTI-AGENT AI APPROACH FOR SAFEGUARDING DIGITAL FINANCIAL SERVICES
Keywords:
artificial intelligence, DDoS attacks, multi-agent systems, digital financial services, cybersecurity, reinforcement learning, anomaly detection, economic security.Abstract
This article examines the application of artificial intelligence–based multi-agent systems in protecting digital financial services from DDoS attacks. Centralized defense systems are often ineffective in countering modern cyberattacks and are characterized by limited adaptability. In the proposed approach, each agent independently monitors network traffic, detects anomalies, and makes real-time decisions through collaborative interaction. Based on adaptive learning, inter-agent communication, and reinforcement learning algorithms, the system continuously updates itself and responds rapidly to emerging threats. Simulation results demonstrate that the multi-agent defense approach enhances the accuracy of DDoS attack detection, reduces response time, and ensures the reliability of financial services, thereby contributing to the strengthening of economic stability.
References
1. Bougueroua, N., Noureddine, A., & Abdelouahid, D. (2021). A Survey on Multi-Agent Based Collaborative Intrusion Detection Systems. Journal of Artificial Intelligence and Soft Computing Research, Vol. 11, No. 2. -pp 111-131.
2. FS-ISAC. (2025). Critical Providers Program and DDoS Maturity Model. New York: Financial Services Information Sharing and Analysis Center. -Operational framework.
3. FS-ISAC & Akamai. (2025). From Nuisance to Strategic Threat: DDoS Attacks Against the Financial Sector - Joint Report Findings. New York: Financial Services Information Sharing and Analysis Center. -48 pp.
4. Qiu, X., Shi, L., & Fan, P. (2025). A Cooperative Intrusion Detection System for IoT Using Fuzzy Logic and CNN Ensemble. Scientific Reports, No. 15. -Article 15934.
5. Funchal, G., Silva, M., Rocha, A., & Costa, P. (2025). Distributed Machine Learning and Multi-Agent Systems for Enhanced Attack Detection in IoT Networks. Proceedings of the International Conference on Information Systems Security and Privacy (ICISSP). Lisbon: SciTePress. -pp 192-203.
6. Aydin, H., & Aydin, M. A. (2025). A Multi-Agent-Based DDoS Detection and Defense System Design with Federated Learning and Blockchain in Public Cloud. Cluster Computing, Vol. 28, No. 16. -pp. 1018-1035.
7. Momin, A. (2025). Defense at Scale: How Agentic AI Secures Without Extra Headcount. CIO.com. -Online analytical report.
8. Wheeler, K. (2024). DDoS Attacks Surge 49% as Hackers Target Financial Sector. Cyber Magazine, No. 10. -pp 26-29.
9. Bonavita, C. (2025). The Evolving DDoS Threat Landscape: How AI is Reshaping Cybersecurity Defense. CIO Influence. -Online industry analysis.
