AI-Driven Cyber security Threat Monitoring and Network Intelligence Dashboard Using Django

Abstract

In the modern digital era, the rapid expansion of networked systems has significantly increased the risk of cyber threats, making cyber security a critical concern for organizations. Traditional security monitoring systems often fail to provide real-time insights and actionable intelligence required to mitigate sophisticated attacks. This project presents the design and implementation of an AI-driven cyber security threat monitoring and network intelligence dashboard using the Django web framework. The proposed system integrates real-time data visualization, event tracking, and network performance monitoring into a unified dashboard. It is designed to detect, classify, and manage security threats such as Distributed Denial of Service (DDoS) attacks, SQL injection attempts, and brute-force login activities. The system employs structured data models including Security Event, Network Metric, and Business Process to organize and analyze security-related information effectively. The dashboard provides administrators with an intuitive interface to monitor recent security events, assess network health, and evaluate the operational status of critical business processes. Threat levels are dynamically computed based on unresolved highseverity events, enabling proactive decision-making. Additionally, simulated network metrics such as traffic flow, latency, and packet loss offer insights into network performance and potential anomalies. One of the key features of the system is its ability to categorize threats by severity levels (Low, Medium, High, and Critical) and allow administrators to resolve incidents efficiently. The integration of seed data generation ensures that the system remains functional and demonstrative even in the absence of realtime data sources. The use of Django provides a robust and scalable backend, while its built-in ORM simplifies database interactions. The system is designed with modularity and extensibility in mind, allowing future integration with machine learning models for predictive threat detection and anomaly analysis. This project demonstrates how webbased technologies can be leveraged to build intelligent cyber security solutions. It highlights the importance of real-time monitoring, centralized management, and datadriven decision-making in safeguarding digital infrastructure. The proposed system not only enhances situational awareness but also reduces response time to potential threats, making it a valuable tool for modern cyber security operations.