HDLIDP: A Hybrid Deep Learning Intrusion Detection and Prevention Framework

作     者：Magdy M.Fadel Sally M.El-Ghamrawy Amr M.T.Ali-Eldin Mohammed K.Hassan Ali I.El-Desoky 

作者机构：Computer Engineering and Systems DepartmentFaculty of EngineeringMansoura UniversityMansoura35516DKEgypt Head of Communications and Computer Engineering DepartmentMISR Higher Institute for Engineering and TechnologyMansoura35111DKEgypt Mechatronics DepartmentFaculty of EngineeringHours University in Egypt(HUE)New Damietta34517DTEgypt 

出 版 物：《Computers, Materials & Continua》 (计算机、材料和连续体（英文）)

年 卷 期：2022年第73卷第11期

页      面：2293-2312页

核心收录：

学科分类：08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

主　　题：Software defined networks(SDN) distributed denial of service attack(DDoS) signature-based detection whale optimization algorism(WOA) deep learning neural network classifier 

摘      要：Distributed denial-of-service(DDoS)attacks are designed to interrupt network services such as email servers and webpages in traditional computer ***,the enormous number of connected devices makes it difficult to operate such a network *** defined networks(SDN)are networks that are managed through a centralized control system,according to *** controller is the brain of any SDN,composing the forwarding table of all data plane network *** the advantages of SDN controllers,DDoS attacks are easier to perpetrate than on traditional *** the controller is a single point of failure,if it fails,the entire network will *** paper offers a Hybrid Deep Learning Intrusion Detection and Prevention(HDLIDP)framework,which blends signature-based and deep learning neural networks to detect and prevent *** framework improves detection accuracy while addressing all of the aforementioned *** validate the framework,experiments are done on both traditional and SDN datasets;the findings demonstrate a significant improvement in classification accuracy.