Enhanced Security Through Intelligent Risk-Based Authentication: Leveraging Big Data and Machine Learning for Real-Time Threat Mitigation

With today's advancements in technology, security has become one of the most important, if not the most important, concerns. These days, strong passwords alone are not enough to protect us from attackers, especially since most people don't know how to protect themselves. In this paper, we explore a Risk-Based Authentication (RBA) system designed for the expansive data networks of today's digital era. Drawing from a dataset that simulates over 33 million authentication events in Norway, the us-ers used this single sign-on (SSO) to access sensitive data provided by the online service, e.g., cloud storage and billing information. The synthesized dataset can reproduce these results made by the original dataset. Our approach integrates machine learning to dynamically adjust security measures in response to per-ceived risks, providing a balanced user experience without com-promising on security. This synthesized dataset enables us to model and test our RBA system's performance, paving the way for advancements in authentication security measures in large-scale online services.