AI-DRIVEN INTRUSION DETECTION SYSTEM FOR FUTURE 5G NETWORKS

Abstract

Fifth-generation (5G) communication networks have evolved rapidly, significantly improving network connectivity, data transmission speed and the number of connected devices. However, these advancements also introduce new security challenges, as traditional intrusion detection systems are often ineffective in dealing with sophisticated and dynamic cyber threats. This paper proposes an artificial intelligence (AI)-based intrusion detection system designed to enhance the security of future 5G networks. The proposed framework utilizes machine learning and deep learning techniques to analyse large-scale network traffic and detect malicious activities in real time. The system is capable of identifying multiple categories of cyberattacks, including denial-of-service attacks, unauthorized access and abnormal network behavior. To evaluate the effectiveness of the proposed model, experiments are conducted using benchmark intrusion detection datasets such as NSL-KDD and CICIDS2017, which represent high-speed and large-scale network environments similar to 5G infrastructures. The performance of the model is assessed using standard evaluation metrics including detection accuracy, precision, recall and processing efficiency. Experimental results demonstrate that the AI-based intrusion detection framework significantly improves the detection of complex and evolving cyber threats compared with traditional rule-based security systems. The proposed solution provides a smart and scalable security framework capable of protecting next-generation 5G network infrastructure while ensuring reliable and secure communication in modern digital environments.

Keywords : Artificial Intelligence, Intrusion Detection System, 5G Networks, Machine Learning, Deep Learning, Network Security, Cyberattack Detection.