Machine Learning-Enabled Techniques for Anomaly Detection in 5G Networks

With the rapid evolution of 5G networks, ensuring robust cyber security measures has become imperative. 5G Network has become a pivotal technology within the new generation ecosystem, facilitating streamlined resource distribution, personalized services, and the provision of diverse applications. This paper introduces a comprehensive Model for detecting attacks in 5G network environment. Leveraging a dataset 5G-SliciNdd specific curated for 5 G network attacks, we employ hybrid feature selection approach to determine the most relevant features for anomaly detection. Several machine learning models are applied to detect and classify attacks accurately. Our methodology focuses on enhancing key performance metrics including false detection rate, accuracy, F1-score, recall, and precision thereby fortifying the security posture of 5 G network against evolving threats. Results of this experiment illustrate the effectiveness of our approach in accurately identifying and mitigating network attacks, contributing to the advancement of malicious traffic detection in next generation communication network.