In this review, we propose a cybersecurity framework aimed at enhancing fraud detection in financial systems by leveraging artificial intelligence (AI), microservices, and RESTful architectures. With the increasing sophistication of cyber threats targeting financial institutions, traditional security methods often fall short in providing comprehensive protection. This review outlines how AI and microservices can be integrated to secure sensitive financial data and improve fraud detection. The framework employs AI-driven models for real-time anomaly detection, enabling systems to quickly identify suspicious activities and predict fraud patterns before they escalate. Microservices architecture, built using technologies such as Java Spring Boot, enables scalability, flexibility, and enhanced communication between modular components through secure RESTful APIs. Angular is utilized for building secure user interfaces, ensuring data protection across front-end applications. Additionally, the integration of security testing platforms such as SonarQube and Blackduck plays a critical role in continuously monitoring and inspecting code for vulnerabilities, ensuring that any flaws in the system are promptly addressed. This comprehensive approach not only safeguards financial institutions from potential fraud but also strengthens the U.S. financial infrastructure, contributing to the nation’s defense against cyber threats. By leveraging cutting-edge technologies and best practices, this framework offers a scalable, secure, and adaptive solution for the evolving challenges in cybersecurity and fraud prevention within the financial sector. The proposed framework enhances operational efficiency while mitigating risks, making it a valuable addition to modern cybersecurity strategies Keywords: Cybersecurity Framework, Fraud Detection, Financial Systems, Microservices, Artificial intelligence.
Read full abstract