Defense Strategies for Epidemic Cyber Security Threats Modeling And Anlaysis By Using ML
International Research Journal of Modernization in Engineering Technology and Science · 2025
In the rapidly evolving digital cybersecurity threats have become more sophisticated, frequent and targeted.Organizations and individuals alike are increasingly exposed to risks such as financial fraud, identity theft, phishing attacks, and data breaches.Traditional cybersecurity frameworks are often reactive, responding to incidents after they occur rather than preventing them proactively.Moreover, they are largely infrastructurecentric and fail to incorporate the behavior and context of individual users into their decision making processes.This project proposes a user centric Machine Learning Framework for Cybersecurity Operations center (CSOC), which aims to bridge the critical gap by integrating behavioral analytics with machine learning to provide personalized, real-time threat alerts.The system monitors user activities-particularly financial transactions-and identifies abnormal behavior patterns using supervised and unsupervised machine learning techniques.When a potential threat, such as an unusually high amount transaction amount, is detected, the system immediately generates an alert message tailored to the specific user, empowering them to take timely action.The platform includes a clean, interactive web interface where users manage their profiles, analyze historical data, view system-generates alerts, and monitor their transaction activities.By incorporating user context into the security framework, this solution not only enhances detection accuracy but also improves user awareness, accountability, and engagement in their own digital security.