AI-based secure event-driven serverless architecture for scalable digital civic participation platform

Area of Science:

• Computer Science
• Urban Planning
• Artificial Intelligence

Background:

• Digitalization of urban governance necessitates scalable, transparent, and secure e-participation platforms.
• Existing systems face challenges in scalability, regulatory compliance, digital sovereignty, and secure citizen authentication.
• Growing demand for intelligent decision-making in smart cities requires advanced digital civic engagement solutions.

Purpose of the Study:

• To propose an AI-based Secure Event-driven Serverless Participation Architecture (SESPA) for next-generation digital e-participation services.
• To address challenges in scalability, security, regulatory compliance, and digital sovereignty in e-participation systems.
• To introduce a hybrid data localization model ensuring data sovereignty for Kazakhstan.

Main Methods:

• Developed SESPA based on the Citizen Participation Event Model (CPEM), treating citizen interactions as events.
• Integrated AI modules for biometric verification and anomaly detection within an event-driven serverless paradigm.
• Implemented a hybrid data localization model separating sensitive citizen data and anonymized analytical events.

Main Results:

• Experimental prototype demonstrated stable latency and efficient scalability under high user loads (up to 10,000 concurrent users).
• AI modules added minimal latency while enabling precise detection of anomalous participation behavior.
• Reduced total cost of ownership compared to Kubernetes-based deployments.

Conclusions:

• SESPA effectively combines serverless computing, AI security, and hybrid data localization for a secure, scalable, and compliant platform.
• The framework supports high citizen engagement, digital sovereignty, and intelligent decision-making for smart city applications.
• SESPA offers a cost-efficient and high-performance technological foundation for future digital civic engagement.