Published Paper Details:

The security of a 5G wireless network will be challenged by a wide range of sophisticated hacking methods. We propose and develop a novel cooperative attack detection method that makes use of a hierarchical Reinforcement Learning (RL) mechanism in order to better identify network assaults and focus on protecting 5G wireless networks from the most severe and cutting-edge forms of network assault, such as DDoS and jamming. Distributed detection systems are operated at the several important nodes of the 5G network (AP, BTS, and servers) to accomplish the cooperative detection. Results from our trials show that the suggested RL detection system improves the ability to identify novel malicious actions and assaults. All network activity is analysed for malicious behaviour using IDS powered by machine learning. Enhancing the intrusion detection system's detection rate was the primary objective of the system design, with a focus on false negative and false positive performance measures. Different machine learning models, including SVM and KNN classifiers, are built and compared.