Increasing importance of computer system security necessitates innovative approaches to user authentication. This study addresses this need by proposing an advanced method utilizing behavioral biometrics and the analysis of HTTP request logs for continuous user authentication within network systems. Employing user-specific Adaptive Neuro-Fuzzy Inference Systems (ANFIS) and an authentication neural network, our research aims to significantly enhance network security by accurately identifying and profiling users based on their software interactions. Notably, our approach is capable of managing extensive user data in real-time, ensuring timely and effective authentication. By leveraging firewall logs, our system achieves high accuracy in attributing network activity to specific users, thus fortifying network defenses against unauthorized access. This research not only contributes to the advancement of network security but also holds promise for practical applications in various domains.