Intelligent Access Control for Secure Financial Microservices Using AI-Driven Threat Detection and Risk Analytics
DOI:
https://doi.org/10.63282/3050-9246.IJETCSIT-V5I1P124Keywords:
Financial Microservices, Intelligent Access Control, Zero-Trust Security, Artificial Intelligence, Threat Detection, Risk Analytics, Explainable AIAbstract
Tackling distributed authentication, inter-service communication, untrusted APIs as well as the ever-evolving cyber threat and fraudulent transaction landscape are all major issues in today's financial application microservice era. The standard methodologies of controlling access – especially static RBAC – are not as contextually aware or flexible as necessary to safeguard the changing relationships among money. This study suggests an intelligent setup of an access control system that integrates Zero Trust Security (ZTS), Artificial Intelligence (AI) based threat detection, Dynamic Trust Assessment (DTA) and Financial Risk Analytics (FRA) to enhance the security of Financial microservices. All the above is covered in one security architecture and framework; ID verification, contextual authorization, API anomaly detection and behavior analysis and explainable risk assessment. Machine learning models are used to analyze the trends of API calls, service interactions across distributed systems, authentication events and behavior indicators of transactions to detect potentially malicious activity. A dynamic policy engine is then used to determine which ones are granted access for, depending on the risk assessment and vulnerabilities of the service and security context. Explainable AI mechanisms offer insight to authorisation decisions while privacy aware information sharing enables safe collaboration, of financial services dispersed at locations. A critical analysis of the proposed framework of architecture in terms of feasibility, scalability, robustness, interpretability and applicability to the operation is provided. To enhance the resilience and trustworthiness of financial microservice ecosystem, the concept of integrated security solution: intelligent threat detection & adaptive authorization and financial risk management is proposed in the article.
References
[1] Li, Z., Du, X., Wu, X., Liu, A., & Wang, S. (2023). Trust-based access control and game-theoretic optimization for microservice architectures. IEEE Transactions on Services Computing, 16(5), 3410–3422. https://doi.org/10.1109/TSC.2023.3251204
[2] Wang, R., Li, C., Zhang, K., & Tu, B. (2023). Zero-trust dynamic access control framework for cloud computing environments. Journal of Network and Computer Applications, 211, Article 103550. https://doi.org/10.1016/j.jnca.2023.103550
[3] Valavala, S. K. (2023). Applying zero trust to financial microservices through default deny authorization. International Journal of Engineering & Extended Technologies Research, 5(3), 6627–6637.
[4] Alboqmi, R., & Gamble, R. F. (2022). Vulnerability-driven trust management for secure microservice mesh architectures. IEEE Access, 10, 89412–89425. https://doi.org/10.1109/ACCESS.2022.3199120
[5] Chang, J., Shi, L., Li, Z., Zuo, X., & Hou, B. (2023). Anomaly detection for API call sequences in microservices using convolutional neural networks. Computers & Security, 128, Article 103140. https://doi.org/10.1016/j.cose.2023.103140
[6] Wei, X., Sun, C.-A., Yang, P., Zhang, X.-Y., & Towey, D. (2023). Log-based anomaly detection in microservice systems using hybrid event sequences. Journal of Systems and Software, 201, Article 111680. https://doi.org/10.1016/j.jss.2023.111680
[7] Li, W., Liu, X., Su, J., & Cui, T. (2023). Transparent machine learning frameworks for effective financial fraud detection and risk management. Expert Systems with Applications, 215, Article 119342. https://doi.org/10.1016/j.eswa.2022.119342
[8] Aljunaid, S. K., Almheiri, S. J., Dawood, H., & Khan, M. A. (2023). Explainable federated learning for secure and transparent financial fraud detection. IEEE Access, 11, 45120–45135. https://doi.org/10.1109/ACCESS.2023.3271102
[9] Vijayanand, D., & Smrithy, G. S. (2023). Explainable ensemble learning models for fraud detection in mobile financial transactions. Journal of Information Security and Applications, 74, Article 103460. https://doi.org/10.1016/j.jisa.2023.103460
[10] Flora, J., & Antunes, N. (2023). Benchmarking intrusion detection systems for microservice applications: Datasets and evaluation methodologies. Software: Practice and Experience, 53(8), 1625–1648. https://doi.org/10.1002/spe.3205
[11] Hore, S., Ghadermazi, J., Shah, A., & Bastian, N. D. (2023). A robust deep learning sequential framework for network intrusion detection. Journal of Information Security and Applications, 72, Article 103395. https://doi.org/10.1016/j.jisa.2022.103395
[12] Lin, Y.-D., Yang, S.-Y., Sudyana, د., Yudha, F., Lai, Y.-C., & Hwang, R.-H. (2022). Multi-datasource machine learning for attack lifecycle and technique detection in enterprise networks. IEEE Transactions on Network and Service Management, 19(4), 4820–4834. https://doi.org/10.1109/TNSM.2022.3198754
[13] Panahandeh, M., Hamou-Lhadj, A., Hamdaqa, M., & Miller, J. (2023). Distributed tracing and performance metrics for microservice anomaly detection. IEEE Transactions on Reliability, 72(2), 789–803. https://doi.org/10.1109/TR.2022.3218931
[14] Plazas Olaya, M. K., Vergara Tejada, J. A., & Aedo Cobo, J. E. (2022). Real-time machine learning anomaly detection for securing microservices-based IoT architectures. Security and Communication Networks, 2022, Article 5849120. https://doi.org/10.1155/2022/5849120
[15] Venčkauskas, A., Kukta, D., Grigaliūnas, Š., & Brūzgienė, R. (2023). Enhancing microservices security with token-based access control method. Sensors, 23(6), Article 3363. https://doi.org/10.3390/s23063363
[16] Al-Wadi, R. A., & Maaita, A. A. (2023). Authentication and role-based authorization in microservice architecture: A generic performance-centric design. Journal of Advances in Information Technology, 14(4), 758–768. https://doi.org/10.12720/jait.14.4.758-768
