Augmenting IoT Intrusion Detection System Performance Using Deep Neural Network

作     者：Nasir Sayed Muhammad Shoaib Waqas Ahmed Sultan Noman Qasem Abdullah M.Albarrak Faisal Saeed 

作者机构：Department of Computer ScienceIslamia College PeshawarPeshawar25120Pakistan Department of Computer ScienceCECOS University of IT and Emerging SciencesPeshawar25000Pakistan Department of Electrical EngineeringHITEC University TaxilaTaxila47080Pakistan Computer Science DepartmentCollege of Computer and Information SciencesImam Mohammad Ibn Saud Islamic University(IMSIU)Riyadh11432Saudi Arabia DAAI Research GroupDepartment of Computing and Data ScienceSchool of Computing and Digital TechnologyBirmingham City UniversityBirminghamB47XGUK 

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

年 卷 期：2023年第74卷第1期

页      面：1351-1374页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 0839[工学-网络空间安全] 08[工学] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：funded by Imam Mohammad Ibn Saud Islamic University RG-21-07-04 

主　　题：Internet of things intrusion detection system deep learning convolutional neural network supervised learning 

摘      要：Due to their low power consumption and limited computing power,Internet of Things(IoT)devices are difficult to ***,the rapid growth of IoT devices in homes increases the risk of *** detection systems(IDS)are commonly employed to prevent *** systems detect incoming attacks and instantly notify users to allow for the implementation of appropriate *** have been made in the past to detect new attacks using machine learning and deep learning techniques,however,these efforts have been *** this paper,we propose two deep learning models to automatically detect various types of intrusion attacks in IoT ***,we experimentally evaluate the use of two Convolutional Neural Networks(CNN)to detect nine distinct types of attacks listed in the NF-UNSW-NB15-v2 *** accomplish this goal,the network stream data were initially converted to twodimensional images,which were then used to train the neural network *** also propose two baseline models to demonstrate the performance of the proposed ***,both models achieve high accuracy in detecting the majority of these nine attacks.