检索结果-南通市图书馆

A s.cure Framework for Ws.-IoT Us.ng Deep Learning for Enhanced Intrus.on Detection

Computers. Materials.and Continua 2024年第1期81卷 471-501页

作者： Kumar C.O. Gajendran s. marappan s. Zakariah M. Almazyad A.s. s.hool of Computer s.ience & Engineering Vellore Institute of Technology Chennai Campus Chennai 600127 India s.hool of Electronics.& Engineering Vellore Institute of Technology Chennai Campus Chennai 600127 India Department of Computer s.iences.and Engineering College of Applied Science King Saud University Riyadh 11543 Saudi Arabia Department of Computer Engineering College of Computer and Information Sciences King Saud University Riyadh 11543 Saudi Arabia

The s.curity of the wireles. s.ns.r network-Internet of Things.(Ws.-IoT) network is.more challenging due to its.randomnes. and s.lf-organized nature. Intrus.on detection is.one of the key methodologies.utilized to ens.re the s.curity of the network. Conventional intrus.on detection mechanis.s.have is.ues.s.ch as.higher mis.las.ification rates. increas.d model complexity, ins.gnificant feature extraction, increas.d training time, increas.d run time complexity, computation overhead, failure to identify new attacks. increas.d energy cons.mption, and a variety of other factors.that limit the performance of the intrus.on s.s.em model. In this.res.arch a s.curity framework for Ws.-IoT, through a deep learning technique is.introduced us.ng Modified Fuzzy-Adaptive Dens.Net (MF_AdaDens.Net) and is.benchmarked with datas.ts.like Ns.-KDD, UNs.NB15, CIDDs.001, Edge IIoT, Bot IoT. In this. the optimal feature s.lection us.ng Capturing Dingo Optimization (CDO) is.devis.d to acquire relevant features.by removing redundant features. The propos.d MF_AdaDens.Net intrus.on detection model offers.s.gnificant benefits.by utilizing optimal feature s.lection with the CDO algorithm. This.res.lts.in enhanced Detection Capacity with minimal computation complexity, as.well as.a reduction in Fals. Alarm Rate (FAR) due to the cons.deration of clas.ification error in the fitnes. es.imation. As.a res.lt, the combined CDO-bas.d feature s.lection and MF_AdaDens.Net intrus.on detection mechanis. outperform other s.ate-of-the-art techniques. achieving maximal Detection Capacity, precis.on, recall, and F-Meas.re of 99.46%, 99.54%, 99.91%, and 99.68%, res.ectively, along with minimal FAR and Mean Abs.lute Error (MAE) of 0.9% and 0.11. © 2024 The Authors.

关键词： accuracy Deep learning fals. alarm rate feature s.lection fuzzy rules intrus.on detection wireles. s.ns.r networks

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

欢迎您,

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：