{"title":"利用联合注意力神经网络进行边缘物联网入侵检测","authors":"Xiedong Song, Qinmin Ma","doi":"10.1007/s10723-023-09725-3","DOIUrl":null,"url":null,"abstract":"<p>Edge nodes, which are expected to grow into a multi-billion-dollar market, are essential for detection against a variety of cyber threats on Internet-of-Things endpoints. Adopting the current network intrusion detection system with deep learning models (DLM) based on FedACNN is constrained by the resource limitations of this network equipment layer. We solve this issue by creating a unique, lightweight, quick, and accurate edge detection model to identify DLM-based distributed denial service attacks on edge nodes. Our approach can generate real results at a relevant pace even with limited resources, such as low power, memory, and processing capabilities. The Federated Convolution Neural Network (FedACNN) deep learning method uses attention mechanisms to minimise communication delay. The developed model uses a recent cybersecurity dataset deployed on an edge node simulated by a Raspberry Pi (UNSW 2015). Our findings show that, compared to traditional DLM methodologies, our model retains a high accuracy rate of about 99%, even with decreased CPU and memory resource use. Also, it is about three times smaller in volume than the most advanced model while requiring a lot less testing time.</p>","PeriodicalId":54817,"journal":{"name":"Journal of Grid Computing","volume":"60 1","pages":""},"PeriodicalIF":3.6000,"publicationDate":"2024-01-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Intrusion Detection using Federated Attention Neural Network for Edge Enabled Internet of Things\",\"authors\":\"Xiedong Song, Qinmin Ma\",\"doi\":\"10.1007/s10723-023-09725-3\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>Edge nodes, which are expected to grow into a multi-billion-dollar market, are essential for detection against a variety of cyber threats on Internet-of-Things endpoints. Adopting the current network intrusion detection system with deep learning models (DLM) based on FedACNN is constrained by the resource limitations of this network equipment layer. We solve this issue by creating a unique, lightweight, quick, and accurate edge detection model to identify DLM-based distributed denial service attacks on edge nodes. Our approach can generate real results at a relevant pace even with limited resources, such as low power, memory, and processing capabilities. The Federated Convolution Neural Network (FedACNN) deep learning method uses attention mechanisms to minimise communication delay. The developed model uses a recent cybersecurity dataset deployed on an edge node simulated by a Raspberry Pi (UNSW 2015). Our findings show that, compared to traditional DLM methodologies, our model retains a high accuracy rate of about 99%, even with decreased CPU and memory resource use. Also, it is about three times smaller in volume than the most advanced model while requiring a lot less testing time.</p>\",\"PeriodicalId\":54817,\"journal\":{\"name\":\"Journal of Grid Computing\",\"volume\":\"60 1\",\"pages\":\"\"},\"PeriodicalIF\":3.6000,\"publicationDate\":\"2024-01-20\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Grid Computing\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://doi.org/10.1007/s10723-023-09725-3\",\"RegionNum\":2,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"COMPUTER SCIENCE, INFORMATION SYSTEMS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Grid Computing","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1007/s10723-023-09725-3","RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, INFORMATION SYSTEMS","Score":null,"Total":0}
Intrusion Detection using Federated Attention Neural Network for Edge Enabled Internet of Things
Edge nodes, which are expected to grow into a multi-billion-dollar market, are essential for detection against a variety of cyber threats on Internet-of-Things endpoints. Adopting the current network intrusion detection system with deep learning models (DLM) based on FedACNN is constrained by the resource limitations of this network equipment layer. We solve this issue by creating a unique, lightweight, quick, and accurate edge detection model to identify DLM-based distributed denial service attacks on edge nodes. Our approach can generate real results at a relevant pace even with limited resources, such as low power, memory, and processing capabilities. The Federated Convolution Neural Network (FedACNN) deep learning method uses attention mechanisms to minimise communication delay. The developed model uses a recent cybersecurity dataset deployed on an edge node simulated by a Raspberry Pi (UNSW 2015). Our findings show that, compared to traditional DLM methodologies, our model retains a high accuracy rate of about 99%, even with decreased CPU and memory resource use. Also, it is about three times smaller in volume than the most advanced model while requiring a lot less testing time.
期刊介绍:
Grid Computing is an emerging technology that enables large-scale resource sharing and coordinated problem solving within distributed, often loosely coordinated groups-what are sometimes termed "virtual organizations. By providing scalable, secure, high-performance mechanisms for discovering and negotiating access to remote resources, Grid technologies promise to make it possible for scientific collaborations to share resources on an unprecedented scale, and for geographically distributed groups to work together in ways that were previously impossible. Similar technologies are being adopted within industry, where they serve as important building blocks for emerging service provider infrastructures.
Even though the advantages of this technology for classes of applications have been acknowledged, research in a variety of disciplines, including not only multiple domains of computer science (networking, middleware, programming, algorithms) but also application disciplines themselves, as well as such areas as sociology and economics, is needed to broaden the applicability and scope of the current body of knowledge.