A Distributed Denial Service Attack Intrusion Detection System for 5G Networks in Internet of Things using a Hybrid Deep Learning Model

5G offers significantly faster speeds, ultra-low latency, and massive capacity compared to previous generations. 5G is designed to connect virtually everything, enabling new applications like enhanced mobile broadband, mission-critical communications, and a massive Internet of Things. While these advancements offer immense opportunities, they also introduce novel complexities and expand the attack surface, presenting significant security challenges, specifically Distributed Denial of Service Attack. This study aims in developing an Intrusion Detection system for 5G enabled Internet of Things using a hybrid deep learning model. The goal of the intrusion detection technique is to create a predictive model that can differentiate between normal and abnormal connections, which are referred to as intrusions or attacks. The study compared six deep learning models including the hybrid model. For performance evaluation we used Google Colab as our simulation environment. Additionally, we used performance metrics; accuracy, recall, precision, false alarm rate, and f1-score. In our findings we find that the hybrid model performed better compared to the other models because this architecture combines the strengths of both neural network types to provide a comprehensive and robust defence mechanism