Performance Comparison of NWDAF-Based Security Analytics Techniques in 5G/B5G Networks

This paper evaluates the performance of NWDAF-based security analytics techniques in 5G/B5G networks, focusing on anomaly detection for network security incidents. Utilizing a 5G testbed, the study examines both statistical methods (Z-Score, MAD, Hampel Filter) and machine learning techniques (Isolation Forest, LOF, One-Class SVM) for the detection of control-plane and data-plane DoS/DDoS attacks. Results indicate a better performance of statistical methods over ML algorithms in such volume-based attacks and suggest a hybrid approach, combining statistical and ML methods, to enhance anomaly detection and adapt to diverse network conditions for improved 5G security.