Detection and Prediction of Inter-Slice Handover DDoS Attacks in ۵G and Beyond Networks Using P۴ and Deep Learning

This study addresses the challenge of securing ۵G and beyond (۶G) networks against Distributed Denial of Service (DDoS) attacks during inter-slice handovers. A hybrid model based on P۴ programmable switches and the Gated Recurrent Unit (GRU) algorithm is proposed to detect and predict such attacks with high accuracy and low latency. P۴ enables real-time extraction of key Quality of Service (QoS) parameters, including packet loss rate, latency, and priority, which are used for efficient traffic analysis and attack detection. The proposed model achieves a DDoS detection accuracy of ۹۸.۶۳%, sensitivity of ۹۸.۵۳%, and an F۱ score of ۹۸.۵۸%, while predicting legitimate slices with an accuracy of ۹۸.۷%. The false positive rate (FPR) is reduced to less than ۲.۱%, and the total system delay for detection and decision-making is kept below ۳۵۰ milliseconds, making it suitable for latency-sensitive applications such as URLLC. Scalability tests demonstrate that the system maintains over ۹۰% detection accuracy and a delay of less than ۵۰۰ milliseconds with up to ۱۵ switches and ۴ slices, even under high traffic loads. This research highlights the effectiveness of combining deep learning with P۴ for enhancing security and scalability in advanced networks, providing a robust framework for next-generation network security.

کلیدواژه ها:

Software-defined networks ، Distributed denial of service attack ، Inter-Slice Handover ، Deep Learning ، Fifth Generation ، Sixth Generation