Intrusion Detection Based on Bidirectional Long Short-Term Memory with Attention Mechanism

作     者：Yongjie Yang Shanshan Tu Raja Hashim Ali Hisham Alasmary Muhammad Waqas Muhammad Nouman Amjad 

作者机构：Engineering Research Center of Intelligent Perception and Autonomous ControlFaculty of Information TechnologyBeijing University of TechnologyBeijing100124China Faculty of Computer Science and EngineeringGIK Institute of Engineering Sciences and TechnologyTopi23460Pakistan Department of Computer ScienceCollege of Computer ScienceKing Khalid UniversityAbhaSaudi Arabia Information Security and Cybersecurity UnitKing Khalid UniversityAbhaSaudi Arabia Computer Engineering DepartmentCollege of Information TechnologyUniversity of Bahrain32038Bahrain School of EngineeringEdith Cowan UniversityJoondalup PerthWA6027Australia School of EngineeringUniversity of Management and TechnologyLahorePakistan 

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：801-815页

核心收录：

学科分类：0831[工学-生物医学工程（可授工学、理学、医学学位）] 1002[医学-临床医学] 08[工学] 081203[工学-计算机应用技术] 0804[工学-仪器科学与技术] 0805[工学-材料科学与工程（可授工学、理学学位）] 0835[工学-软件工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：the Beijing Natural Science Foundation(No.4212015) Natural Science Foundation of China(No.61801008) China Ministry of Education-China Mobile Scientific Research Foundation(No.MCM20200102) China Postdoctoral Science Foundation(No.2020M670074) Beijing Municipal Commission of Education Foundation(No.KM201910005025) the Deanship of Scientific Research at King Khalid University for funding this work through large groups Project under Grant Number RGP.2/201/43. 

主　　题：Fog computing intrusion detection bi-LSTM attention mechanism 

摘      要：With the recent developments in the Internet of Things(IoT),the amount of data collected has expanded tremendously,resulting in a higher demand for data storage,computational capacity,and real-time processing capabilities.Cloud computing has traditionally played an important role in establishing IoT.However,fog computing has recently emerged as a new field complementing cloud computing due to its enhanced mobility,location awareness,heterogeneity,scalability,low latency,and geographic distribution.However,IoT networks are vulnerable to unwanted assaults because of their open and shared nature.As a result,various fog computing-based security models that protect IoT networks have been developed.A distributed architecture based on an intrusion detection system(IDS)ensures that a dynamic,scalable IoT environment with the ability to disperse centralized tasks to local fog nodes and which successfully detects advanced malicious threats is available.In this study,we examined the time-related aspects of network traffic data.We presented an intrusion detection model based on a twolayered bidirectional long short-term memory(Bi-LSTM)with an attention mechanism for traffic data classification verified on the UNSW-NB15 benchmark dataset.We showed that the suggested model outperformed numerous leading-edge Network IDS that used machine learning models in terms of accuracy,precision,recall and F1 score.