Yazar "Hadi, Mhmood Radhi Hadi" seçeneğine göre listele

Listeleniyor 1 - 1 / 1
  • Küçük Resim
    Öğe
    A PROPOSED APPROACH NETWORK INTRUSION DETECTION SYSTEM (NIDS) USING DEEP LEARNING FOR SOFTWARE DEFINED NETWORK (SDN): A FUTURISTIC APPROACH
    (2022-06) Hadi, Mhmood Radhi Hadi
    Software defined networking (SDN) is considered one of the most promising solutions for evolving and modifying the architecture of traditional networks. The most notable features of SDN are many improvements and changes to the network and internet architecture. SDN primary solutions are flexibility and centralized control. Therefore, SDN is completely centralized. The centralization of SDN has created many vulnerabilities in this architecture that have made it a target for attackers. The controller is the brain of the SDN, and once it is attacked, the entire network will fall. One of the most significant topics to consider while considering SDN is attack protection. It is vital to put in place a powerful defense system capable of rapidly detecting attacks. Intrusion detection systems are one of the most significant network security systems. We propose to use these approaches to build an SDN-specific intrusion detection system. The deep learning system has attracted researchers in recent years because of its efficiency. Our approach suggests using an intelligent network intrusion detection system (NIDS) which use deep learning to identify attacks that are trained with deep learning algorithms to achieve reliable and secure systems. We propose to use algorithms (DNN, CNN, RNN, GRU, LSTM) in our proposed approach, which is trained on 12 features extracted from 41 features in NSL-KDD dataset. The results show that the CNN algorithm achieves the highest accuracy, as well as other excellent algorithms with high accuracy. Our approach has been successful so it is expected that deep learning can be effectively used for SDN security in the future.