Detection of DDoS Attack in IoT Networks Using Sample Selected RNN-ELM

• DOI: 10.32604/iasc.2022.022856
• Publication Date: 2022-05-25T06:28:42Z
• Authors: S. Hariprasad; T. Deepa; N. Bharathiraja
• Keywords: Extreme Learning Machine; Neighbor Discovery Protocol; Benchmark (surveying)

The Internet of Things (IoT) is a global information and communication technology which aims to connect any type device the internet at time in location. Nowadays billions IoT devices are connected world, this leads easily cause vulnerability devices. increasing users different IoT-related applications more data attacks happening networks after fog layer. To detect reduce deep learning model used. In article, hybrid sample selected recurrent neural network-extreme machine (hybrid SSRNN-ELM) algorithm that uses network (RNN) as supervised extreme (ELM) classifier unsupervised. proposed features extracting from original dataset using linear regression with recursive feature extraction (LR-RFE) sequence forward selector (SFS) then RNN used learn behavior important end layer ELM This intrusion detection placed between its NSL_KDD benchmark for detecting distributed denial-of-service (DDoS) attack node. SSRNN-ELM exposes while testing enhanced accuracy up 99% NSL-KDD set. Experimental results outperform by technique when compared existing models.