Internet of Things最新文献_第2页

ZFort: A scalable zero-trust approach for trust management and traffic engineering in SDN based IoTs ZFort：基于 SDN 的物联网中信任管理和流量工程的可扩展零信任方法

IF 6 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Internet of Things

Pub Date : 2024-10-29 DOI: 10.1016/j.iot.2024.101419

Usman Ashraf , Mohammed Al-Naeem , Muhammad Nasir Mumtaz Bhutta , Chau Yuen

The Internet of Things (IoT), is a promising solution, but faces critical security challenges in the backdrop of evolving and sophisticated threats. Traditional security models are not well-adopted to protecting these diverse and resource-constrained devices against evolving threats like Advanced Persistent Threats (APTs). We introduce ZFort, a zero-trust framework that prioritizes the security of critical nodes in IoT networks. ZFort dynamically evaluates the risk status of nodes based on node’s criticality and vulnerability scores derived from Common Vulnerabilities and Exposures (CVE) data ZFort dynamically assesses node risk based on criticality and vulnerability scores derived from Common Vulnerabilities and Exposures (CVE) data, and Common Vulnerability Scoring System (CVSS). ZFort uses a stochastic differential equation model for dynamic and continuous trust evaluation between nodes. Based on this evaluation, it dynamically adjusts security measures and routing decisions in real-time. Additionally, ZFort quickly isolates nodes that are likely compromised and prevents routing across them. ZFort uses Mixed Integer Linear Programming (MILP) and efficient heuristics, guaranteeing scalability and resource efficiency even in large networks and enhances the resilience and trustworthiness of key IoT infrastructure.

物联网（IoT）是一种前景广阔的解决方案，但在不断演变的复杂威胁背景下，它面临着严峻的安全挑战。传统的安全模式并不能很好地保护这些多样化、资源有限的设备免受高级持续性威胁（APT）等不断演变的威胁。我们引入了零信任框架 ZFort，该框架优先考虑物联网网络中关键节点的安全。ZFort 根据节点的临界度和来自常见漏洞和暴露（CVE）数据的漏洞评分动态评估节点的风险状态。ZFort 采用随机微分方程模型对节点间的信任度进行动态和连续评估。根据这种评估，它可以动态地实时调整安全措施和路由决策。此外，ZFort 还能快速隔离可能受到攻击的节点，并防止路由穿过这些节点。ZFort 采用混合整数线性规划（MILP）和高效启发式方法，即使在大型网络中也能保证可扩展性和资源效率，并增强关键物联网基础设施的弹性和可信度。

{"title":"ZFort: A scalable zero-trust approach for trust management and traffic engineering in SDN based IoTs","authors":"Usman Ashraf , Mohammed Al-Naeem , Muhammad Nasir Mumtaz Bhutta , Chau Yuen","doi":"10.1016/j.iot.2024.101419","DOIUrl":"10.1016/j.iot.2024.101419","url":null,"abstract":"<div><div>The Internet of Things (IoT), is a promising solution, but faces critical security challenges in the backdrop of evolving and sophisticated threats. Traditional security models are not well-adopted to protecting these diverse and resource-constrained devices against evolving threats like Advanced Persistent Threats (APTs). We introduce <em>ZFort</em>, a zero-trust framework that prioritizes the security of critical nodes in IoT networks. ZFort dynamically evaluates the risk status of nodes based on node’s criticality and vulnerability scores derived from Common Vulnerabilities and Exposures (CVE) data ZFort dynamically assesses node risk based on criticality and vulnerability scores derived from Common Vulnerabilities and Exposures (CVE) data, and Common Vulnerability Scoring System (CVSS). ZFort uses a stochastic differential equation model for dynamic and continuous trust evaluation between nodes. Based on this evaluation, it dynamically adjusts security measures and routing decisions in real-time. Additionally, ZFort quickly isolates nodes that are likely compromised and prevents routing across them. ZFort uses Mixed Integer Linear Programming (MILP) and efficient heuristics, guaranteeing scalability and resource efficiency even in large networks and enhances the resilience and trustworthiness of key IoT infrastructure.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"28 ","pages":"Article 101419"},"PeriodicalIF":6.0,"publicationDate":"2024-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142654830","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Self-enhanced multi-task and split federated learning framework for RIS-aided cell-free systems 用于 RIS 辅助无细胞系统的自增强多任务和分裂联合学习框架

IF 6 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Internet of Things

Pub Date : 2024-10-28 DOI: 10.1016/j.iot.2024.101406

Taisei Urakami , Haohui Jia , Na Chen , Minoru Okada

Collaborative learning-based beamforming schemes have been exploited to improve spectral efficiency (SE) with low privacy risks in reconfigurable intelligent surface (RIS)-aided cell-free (CF) systems. However, a single-task-driven federated learning (FL) scheme needs to run a large model on local devices with limited computing capacity due to its imbalanced computing resources. Although a single-task-driven split learning (SL) can split a large model into multiple smaller portions, it concerns the training time overhead due to its relay-based training. Meanwhile, annotation for well-labeled channel state information (CSI) still affects beamforming performance with high labeling costs. In this paper, we first propose a collaborative learning framework, named multi-task and split federated learning (M-SFL), for joint channel semantic reconstruction and beamforming for RIS-aided CF systems. The proposed M-SFL framework simultaneously tackles channel semantic reconstruction and beamforming with shared knowledge to distinguish the inherent information of user equipments (UEs). The proposed M-SFL splits large model into multiple lightweight parts friendly with the limited computing local devices and trains local and global models parallelly with the Federated server. Then, we expand the proposed M-SFL framework into a self-enhanced multi-task and split federated learning (SM-SFL) framework by integrating the contrastive learning technique. The SM-SFL framework pre-trains by predicting and distinguishing the target CSI and others without annotation, and then we fine-tune the local and global models with limited labeled CSI. Simulation results show that the proposed framework can jointly achieve better channel semantic reconstruction and higher SE with balanced computing resources, faster beamforming, and low labeling costs.

在可重构智能表面（RIS）辅助的无小区（CF）系统中，基于协作学习的波束成形方案被用来提高频谱效率（SE），同时降低隐私风险。然而，由于计算资源不平衡，单任务驱动的联合学习（FL）方案需要在计算能力有限的本地设备上运行大型模型。虽然单任务驱动的拆分学习（SL）可以将大型模型拆分成多个较小的部分，但由于其基于中继的训练，因此会造成训练时间的开销。同时，对标记良好的信道状态信息（CSI）进行标注仍会影响波束成形性能，且标注成本较高。在本文中，我们首先提出了一种协作学习框架，命名为多任务和分裂联合学习（M-SFL），用于 RIS 辅助 CF 系统的联合信道语义重建和波束成形。所提出的 M-SFL 框架利用共享知识同时处理信道语义重建和波束成形问题，以区分用户设备（UE）的固有信息。所提出的 M-SFL 利用计算能力有限的本地设备将大型模型友好地分割成多个轻量级部分，并与联邦服务器并行训练本地和全局模型。然后，我们通过整合对比学习技术，将所提出的 M-SFL 框架扩展为自我增强的多任务和拆分联合学习（SM-SFL）框架。SM-SFL 框架通过预测和区分目标 CSI 和其他无标注的 CSI 进行预训练，然后利用有限的标注 CSI 对局部和全局模型进行微调。仿真结果表明，所提出的框架可以在计算资源均衡、波束成形更快、标注成本更低的情况下，共同实现更好的信道语义重建和更高的 SE。

{"title":"Self-enhanced multi-task and split federated learning framework for RIS-aided cell-free systems","authors":"Taisei Urakami , Haohui Jia , Na Chen , Minoru Okada","doi":"10.1016/j.iot.2024.101406","DOIUrl":"10.1016/j.iot.2024.101406","url":null,"abstract":"<div><div>Collaborative learning-based beamforming schemes have been exploited to improve spectral efficiency (SE) with low privacy risks in reconfigurable intelligent surface (RIS)-aided cell-free (CF) systems. However, a single-task-driven federated learning (FL) scheme needs to run a large model on local devices with limited computing capacity due to its imbalanced computing resources. Although a single-task-driven split learning (SL) can split a large model into multiple smaller portions, it concerns the training time overhead due to its relay-based training. Meanwhile, annotation for well-labeled channel state information (CSI) still affects beamforming performance with high labeling costs. In this paper, we first propose a collaborative learning framework, named multi-task and split federated learning (M-SFL), for joint channel semantic reconstruction and beamforming for RIS-aided CF systems. The proposed M-SFL framework simultaneously tackles channel semantic reconstruction and beamforming with shared knowledge to distinguish the inherent information of user equipments (UEs). The proposed M-SFL splits large model into multiple lightweight parts friendly with the limited computing local devices and trains local and global models parallelly with the Federated server. Then, we expand the proposed M-SFL framework into a self-enhanced multi-task and split federated learning (SM-SFL) framework by integrating the contrastive learning technique. The SM-SFL framework pre-trains by predicting and distinguishing the target CSI and others without annotation, and then we fine-tune the local and global models with limited labeled CSI. Simulation results show that the proposed framework can jointly achieve better channel semantic reconstruction and higher SE with balanced computing resources, faster beamforming, and low labeling costs.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"28 ","pages":"Article 101406"},"PeriodicalIF":6.0,"publicationDate":"2024-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142577838","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Comparative analysis of the standalone and Hybrid SDN solutions for early detection of network channel attacks in Industrial Control Systems: A WWTP case study 用于早期检测工业控制系统中网络通道攻击的独立和混合 SDN 解决方案的比较分析：污水处理厂案例研究

IF 6 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Internet of Things

Pub Date : 2024-10-28 DOI: 10.1016/j.iot.2024.101413

Valentine Machaka , Santiago Figueroa-Lorenzo , Saioa Arrizabalaga , Josune Hernantes

Industrial Control Systems (ICS) are critical to operating various Critical infrastructures (CIs). However, ICS communication channels connecting sensors, actuators, and local and supervisory controllers are vulnerable to network attacks compromising the system’s availability and integrity. This study proposes and compares Standalone and Hybrid Software Defined Networking (SDN) solutions to mitigate (Detect and Respond) network channel attacks in ICS environments. The methodology utilised applies a testbed designed in GNS3 following the IEC 62264 Industrial Automation Pyramid. It incorporates ICS components such as PLCs and SCADA and a Simulink-based digital twin system for a wastewater treatment plant. This research establishes a proof of concept involving detection and response to network channel attacks evaluated through packet thresholds, packet analysis, and cryptographic hashing techniques in SDN. The Mitre attack framework is implemented to provide insight into the system’s vulnerabilities through adversary emulation. The research findings reveal that both SDN solutions effectively enhance ICS network security; the Standalone SDN solution is more suitable for time-sensitive networks, while the Hybrid SDN solution better serves non-time-sensitive industrial environments. While the Standalone SDN solution offers a 75% efficiency improvement, its’ status as a nascent technology introduces unresolved vulnerabilities and limited testing favouring the Hybrid SDN solution, which provides robust security and reliability due to the integration with the Snort IDS. Thus, selecting the appropriate solution requires carefully considering the trade-offs between enhanced performance and established security. In conclusion, this study underscores the potential of SDN solutions in strengthening ICS security and suggests areas for future research.

工业控制系统（ICS）对于各种关键基础设施（CI）的运行至关重要。然而，连接传感器、执行器以及本地和监管控制器的 ICS 通信通道很容易受到网络攻击，从而影响系统的可用性和完整性。本研究提出并比较了独立和混合软件定义网络（SDN）解决方案，以减轻（检测和响应）ICS 环境中的网络通道攻击。采用的方法是根据 IEC 62264 工业自动化金字塔在 GNS3 中设计一个测试平台。它包含了 PLC 和 SCADA 等 ICS 组件，以及一个基于 Simulink 的污水处理厂数字孪生系统。这项研究通过 SDN 中的数据包阈值、数据包分析和加密哈希技术，建立了一个涉及网络通道攻击检测和响应的概念验证。实施了 Mitre 攻击框架，通过对手模拟来深入了解系统的漏洞。研究结果表明，两种 SDN 解决方案都能有效增强 ICS 网络安全；独立 SDN 解决方案更适用于时间敏感型网络，而混合 SDN 解决方案则更适用于非时间敏感型工业环境。虽然独立 SDN 解决方案的效率提高了 75%，但由于其技术刚刚起步，存在尚未解决的漏洞和有限的测试，因此混合 SDN 解决方案更受青睐，因为它与 Snort IDS 集成，可提供强大的安全性和可靠性。因此，要选择合适的解决方案，就必须仔细考虑增强性能和建立安全性之间的权衡。总之，本研究强调了 SDN 解决方案在加强 ICS 安全方面的潜力，并提出了今后的研究领域。

{"title":"Comparative analysis of the standalone and Hybrid SDN solutions for early detection of network channel attacks in Industrial Control Systems: A WWTP case study","authors":"Valentine Machaka , Santiago Figueroa-Lorenzo , Saioa Arrizabalaga , Josune Hernantes","doi":"10.1016/j.iot.2024.101413","DOIUrl":"10.1016/j.iot.2024.101413","url":null,"abstract":"<div><div>Industrial Control Systems (ICS) are critical to operating various Critical infrastructures (CIs). However, ICS communication channels connecting sensors, actuators, and local and supervisory controllers are vulnerable to network attacks compromising the system’s availability and integrity. This study proposes and compares Standalone and Hybrid Software Defined Networking (SDN) solutions to mitigate (Detect and Respond) network channel attacks in ICS environments. The methodology utilised applies a testbed designed in GNS3 following the IEC 62264 Industrial Automation Pyramid. It incorporates ICS components such as PLCs and SCADA and a Simulink-based digital twin system for a wastewater treatment plant. This research establishes a proof of concept involving detection and response to network channel attacks evaluated through packet thresholds, packet analysis, and cryptographic hashing techniques in SDN. The Mitre attack framework is implemented to provide insight into the system’s vulnerabilities through adversary emulation. The research findings reveal that both SDN solutions effectively enhance ICS network security; the Standalone SDN solution is more suitable for time-sensitive networks, while the Hybrid SDN solution better serves non-time-sensitive industrial environments. While the Standalone SDN solution offers a 75% efficiency improvement, its’ status as a nascent technology introduces unresolved vulnerabilities and limited testing favouring the Hybrid SDN solution, which provides robust security and reliability due to the integration with the Snort IDS. Thus, selecting the appropriate solution requires carefully considering the trade-offs between enhanced performance and established security. In conclusion, this study underscores the potential of SDN solutions in strengthening ICS security and suggests areas for future research.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"28 ","pages":"Article 101413"},"PeriodicalIF":6.0,"publicationDate":"2024-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142540366","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Combinative model compression approach for enhancing 1D CNN efficiency for EIT-based Hand Gesture Recognition on IoT edge devices 采用组合模型压缩方法提高基于 EIT 的物联网边缘设备手势识别的一维 CNN 效率

IF 6 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Internet of Things

Pub Date : 2024-10-28 DOI: 10.1016/j.iot.2024.101403

Mahdi Mnif , Salwa Sahnoun , Yasmine Ben Saad , Ahmed Fakhfakh , Olfa Kanoun

Tiny Machine Learning is rapidly evolving in edge computing and intelligent Internet of Things (IoT) devices. This paper investigates model compression techniques with the aim of determining their compatibility when combined, and identifying an effective approach to improve inference speed and energy efficiency within IoT edge devices. The study is carried out on the application scenario of Hand Gesture Recognition (HGR) based on Electrical Impedance Tomography (EIT), which involves complex signal processing and needs real-time processing and energy efficiency. Therefore, a customized 1-Dimensional Convolutional Neural Network (1D CNN) HGR classification model has been designed. An approach based on strategically combining model compression techniques was then implemented resulting in a model customized for faster inference and improved energy efficiency for IoT embedded devices. The model size became compact at 10.42 kB, resulting in a substantial size reduction of 98.8%, and an inference gain of 94.73% on a personal computer with approximately 8.56% decrease in accuracy. The approach of combinative model compression techniques was applied to a wide range of edge-computing IoT devices with limited processing power, resulting in a significant improvement in model execution speed and energy efficiency for these devices. Specifically, there was an average power consumption gain of 52% for Arduino Nano BLE and 34.05% for Raspberry Pi 4. Inference time was halved for Arduino Nano BLE Sense, Nicla Sense, and Raspberry Pi 4, with a remarkable gain of 94% for ESP32.

微型机器学习在边缘计算和智能物联网（IoT）设备中发展迅速。本文对模型压缩技术进行了研究，旨在确定这些技术结合使用时的兼容性，并找出一种有效的方法来提高物联网边缘设备的推理速度和能效。研究针对基于电阻抗断层扫描（EIT）的手势识别（HGR）应用场景展开，该应用场景涉及复杂的信号处理，需要实时处理并提高能效。因此，设计了一个定制的一维卷积神经网络（1D CNN）HGR 分类模型。然后，实施了一种基于模型压缩技术战略组合的方法，从而为物联网嵌入式设备定制了一个推理速度更快、能效更高的模型。模型大小压缩为 10.42 kB，大幅缩小了 98.8%，在个人电脑上的推理增益为 94.73%，准确率降低了约 8.56%。组合模型压缩技术方法被广泛应用于处理能力有限的边缘计算物联网设备，从而显著提高了这些设备的模型执行速度和能效。具体来说，Arduino Nano BLE 和 Raspberry Pi 4 的平均功耗分别增加了 52% 和 34.05%。Arduino Nano BLE Sense、Nicla Sense 和 Raspberry Pi 4 的推理时间缩短了一半，ESP32 的推理时间显著增加了 94%。

{"title":"Combinative model compression approach for enhancing 1D CNN efficiency for EIT-based Hand Gesture Recognition on IoT edge devices","authors":"Mahdi Mnif , Salwa Sahnoun , Yasmine Ben Saad , Ahmed Fakhfakh , Olfa Kanoun","doi":"10.1016/j.iot.2024.101403","DOIUrl":"10.1016/j.iot.2024.101403","url":null,"abstract":"<div><div>Tiny Machine Learning is rapidly evolving in edge computing and intelligent Internet of Things (IoT) devices. This paper investigates model compression techniques with the aim of determining their compatibility when combined, and identifying an effective approach to improve inference speed and energy efficiency within IoT edge devices. The study is carried out on the application scenario of Hand Gesture Recognition (HGR) based on Electrical Impedance Tomography (EIT), which involves complex signal processing and needs real-time processing and energy efficiency. Therefore, a customized 1-Dimensional Convolutional Neural Network (1D CNN) HGR classification model has been designed. An approach based on strategically combining model compression techniques was then implemented resulting in a model customized for faster inference and improved energy efficiency for IoT embedded devices. The model size became compact at 10.42 kB, resulting in a substantial size reduction of 98.8%, and an inference gain of 94.73% on a personal computer with approximately 8.56% decrease in accuracy. The approach of combinative model compression techniques was applied to a wide range of edge-computing IoT devices with limited processing power, resulting in a significant improvement in model execution speed and energy efficiency for these devices. Specifically, there was an average power consumption gain of 52% for Arduino Nano BLE and 34.05% for Raspberry Pi 4. Inference time was halved for Arduino Nano BLE Sense, Nicla Sense, and Raspberry Pi 4, with a remarkable gain of 94% for ESP32.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"28 ","pages":"Article 101403"},"PeriodicalIF":6.0,"publicationDate":"2024-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142572178","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Dynamic IoT deployment reconfiguration: A global-level self-organisation approach 动态物联网部署重组：全球级自组织方法

IF 6 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Internet of Things

Pub Date : 2024-10-28 DOI: 10.1016/j.iot.2024.101412

Nicolas Farabegoli, Danilo Pianini, Roberto Casadei, Mirko Viroli

The edge–cloud continuum provides a heterogeneous, multi-scale, and dynamic infrastructure supporting complex deployment profiles and trade-offs for application scenarios like those found in the Internet of Things and large-scale cyber–physical systems domains. To exploit the continuum, applications should be designed in a way that promotes flexibility and reconfigurability, and proper management (sub-)systems should take care of reconfiguring them in response to changes in the environment or non-functional requirements. Approaches may leverage optimisation-based or heuristic-based policies, and decision making may be centralised or distributed: this work investigates decentralised heuristic-based approaches. In particular, we focus on the pulverisation approach, whereby a distributed software system is automatically partitioned (“pulverised”) into different deployment units. In this context, we address two main research problems: how to support the runtime reconfiguration of pulverised systems, and how to specify decentralised reconfiguring policies by a global perspective. To address the first problem, we design and implement a middleware for pulverised systems separating infrastructural and application concerns. To address the second problem, we leverage aggregate computing and exploit self-organisation patterns to devise self-stabilising reconfiguration strategies. By simulating deployments on different kinds of complex infrastructures, we assess the flexibility of the pulverisation middleware design as well as the effectiveness and resilience of the aggregate computing-based reconfiguration policies.

边缘-云连续体提供了一个异构、多尺度和动态的基础设施，支持复杂的部署配置和权衡，适用于物联网和大规模网络物理系统等应用场景。要利用这一连续体，在设计应用程序时应提高其灵活性和可重构性，而适当的管理（子）系统则应根据环境或非功能性要求的变化对其进行重构。这种方法可以利用基于优化或启发式的政策，决策制定可以是集中式的，也可以是分布式的：这项工作研究的是基于启发式的分散方法。特别是，我们将重点放在 "粉碎 "方法上，即自动将分布式软件系统分割（"粉碎"）成不同的部署单元。在这种情况下，我们主要解决两个研究问题：如何支持粉碎系统的运行时重新配置，以及如何从全局角度指定分散式重新配置策略。为解决第一个问题，我们设计并实施了一种用于粉碎系统的中间件，将基础设施和应用问题分开。为解决第二个问题，我们利用聚合计算和自组织模式来设计自稳定的重新配置策略。通过模拟不同类型复杂基础设施的部署，我们评估了粉碎中间件设计的灵活性以及基于聚合计算的重新配置策略的有效性和弹性。

{"title":"Dynamic IoT deployment reconfiguration: A global-level self-organisation approach","authors":"Nicolas Farabegoli, Danilo Pianini, Roberto Casadei, Mirko Viroli","doi":"10.1016/j.iot.2024.101412","DOIUrl":"10.1016/j.iot.2024.101412","url":null,"abstract":"<div><div>The edge–cloud continuum provides a heterogeneous, multi-scale, and dynamic infrastructure supporting complex deployment profiles and trade-offs for application scenarios like those found in the Internet of Things and large-scale cyber–physical systems domains. To exploit the continuum, applications should be designed in a way that promotes flexibility and reconfigurability, and proper management (sub-)systems should take care of reconfiguring them in response to changes in the environment or non-functional requirements. Approaches may leverage optimisation-based or heuristic-based policies, and decision making may be centralised or distributed: this work investigates decentralised heuristic-based approaches. In particular, we focus on the pulverisation approach, whereby a distributed software system is automatically partitioned (“pulverised”) into different deployment units. In this context, we address two main research problems: how to support the runtime reconfiguration of pulverised systems, and how to specify decentralised reconfiguring policies by a global perspective. To address the first problem, we design and implement a middleware for pulverised systems separating infrastructural and application concerns. To address the second problem, we leverage aggregate computing and exploit self-organisation patterns to devise self-stabilising reconfiguration strategies. By simulating deployments on different kinds of complex infrastructures, we assess the flexibility of the pulverisation middleware design as well as the effectiveness and resilience of the aggregate computing-based reconfiguration policies.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"28 ","pages":"Article 101412"},"PeriodicalIF":6.0,"publicationDate":"2024-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142572262","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Physical unclonable functions and QKD-based authentication scheme for IoT devices using blockchain 使用区块链的物联网设备的物理不可克隆功能和基于 QKD 的身份验证方案

IF 6 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Internet of Things

Pub Date : 2024-10-25 DOI: 10.1016/j.iot.2024.101404

Tyson Baptist D Cunha , Kiran M. , Ritik Ranjan , Athanasios V. Vasilakos

As the number of Internet of Things (IoT) devices is increasing exponentially, strong security measures are needed to guard against different types of cyberattacks. This research offers a novel IoT device authentication technique to mitigate these challenges by integrating three cutting-edge technologies namely blockchain technology, Quantum Key Distribution (QKD), and Physically Unclonable Functions (PUFs). By utilizing the distinctive qualities of PUFs for device identification and the unrivaled security of QKD for key exchange, the proposed approach seeks to address the significant security issues present in IoT environments. Adopting blockchain technology ensures transparency and verifiability of the authentication process across distributed IoT networks by adding an unchangeable, decentralized layer of trust. An examination of the computing and communication costs reveals that the proposed protocol is effective, necessitating low computational resources that are critical for IoT devices with limited resources. The protocol’s resistance against a variety of attacks is demonstrated by formal proofs based on the Real-Or-Random (ROR) model and security evaluations using the Scyther tool, ensuring the integrity and secrecy of communications. Various threats are analyzed, and the protocol is proven to be secure and efficient from all forms of attacks.

随着物联网（IoT）设备的数量呈指数级增长，需要强有力的安全措施来防范不同类型的网络攻击。本研究通过整合区块链技术、量子密钥分发（QKD）和物理不可克隆函数（PUFs）三项前沿技术，提供了一种新型物联网设备认证技术，以减轻这些挑战。通过利用用于设备识别的 PUFs 的独特品质和用于密钥交换的 QKD 的无与伦比的安全性，所提出的方法旨在解决物联网环境中存在的重大安全问题。采用区块链技术可通过增加一个不可更改的分散信任层，确保分布式物联网网络中认证过程的透明度和可验证性。对计算和通信成本的研究表明，所提出的协议是有效的，只需较少的计算资源，这对于资源有限的物联网设备来说至关重要。基于真实或随机（ROR）模型的正式证明和使用 Scyther 工具进行的安全评估证明了该协议可抵御各种攻击，确保了通信的完整性和保密性。对各种威胁进行了分析，并证明该协议在各种形式的攻击面前都是安全高效的。

{"title":"Physical unclonable functions and QKD-based authentication scheme for IoT devices using blockchain","authors":"Tyson Baptist D Cunha , Kiran M. , Ritik Ranjan , Athanasios V. Vasilakos","doi":"10.1016/j.iot.2024.101404","DOIUrl":"10.1016/j.iot.2024.101404","url":null,"abstract":"<div><div>As the number of Internet of Things (IoT) devices is increasing exponentially, strong security measures are needed to guard against different types of cyberattacks. This research offers a novel IoT device authentication technique to mitigate these challenges by integrating three cutting-edge technologies namely blockchain technology, Quantum Key Distribution (QKD), and Physically Unclonable Functions (PUFs). By utilizing the distinctive qualities of PUFs for device identification and the unrivaled security of QKD for key exchange, the proposed approach seeks to address the significant security issues present in IoT environments. Adopting blockchain technology ensures transparency and verifiability of the authentication process across distributed IoT networks by adding an unchangeable, decentralized layer of trust. An examination of the computing and communication costs reveals that the proposed protocol is effective, necessitating low computational resources that are critical for IoT devices with limited resources. The protocol’s resistance against a variety of attacks is demonstrated by formal proofs based on the Real-Or-Random (ROR) model and security evaluations using the Scyther tool, ensuring the integrity and secrecy of communications. Various threats are analyzed, and the protocol is proven to be secure and efficient from all forms of attacks.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"28 ","pages":"Article 101404"},"PeriodicalIF":6.0,"publicationDate":"2024-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142586765","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Analyzing common lexical features of fake news using multi-head attention weights 利用多头注意力权重分析假新闻的共同词汇特征

IF 6 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Internet of Things

Pub Date : 2024-10-24 DOI: 10.1016/j.iot.2024.101409

Mamoru Mimura , Takayuki Ishimaru

Numerous approaches have been developed to identify fake news through machine learning; however, these methods are predominantly assessed using singular datasets specific to certain fields, leading to a scarcity of research on versatile models adaptable to a range of domains. This study evaluates the adaptability of a fake news detection model across diverse fields, employing three distinct datasets. Furthermore, the study leverages the multi-head attention feature of bidirectional encoder representations from transformers (BERT) to scrutinize the feature extraction process in the model. In our analysis, we focused on words that are commonly emphasized by machine learning in fake news detection. The dataset comprised 27,442 instances of genuine news and 28,359 instances of fabricated news, each distinctly labeled. To examine the focal words, we utilized multi-head attention, a component of BERT. This mechanism assigns greater weight to words that receive more attention. Our investigation aimed to identify which words were assigned higher weights in each article. The findings indicate that while representing a minor percentage, a common characteristic of fake news is the heightened attention to words that influence the credibility of the article. To assess the versatility of the model, we applied the model trained on one dataset to classify other datasets. The results demonstrate a notable decline in accuracy, attributable to the distinctive characteristics of the training data. These observations suggest that common features among fake news, which could be extracted using the fine-tuned BERT model, are limited.

通过机器学习识别假新闻的方法层出不穷；然而，这些方法主要是通过特定领域的单一数据集进行评估的，导致有关可适应一系列领域的通用模型的研究十分匮乏。本研究采用三个不同的数据集，评估了假新闻检测模型在不同领域的适应性。此外，本研究还利用变换器双向编码器表征（BERT）的多头注意力特征，对模型中的特征提取过程进行了仔细检查。在分析中，我们重点关注机器学习在假新闻检测中通常会强调的词语。数据集包括 27,442 个真实新闻实例和 28,359 个虚假新闻实例，每个实例都有不同的标签。为了检测焦点词，我们使用了多头注意力，这是 BERT 的一个组成部分。这一机制为受到更多关注的词语分配了更大的权重。我们的调查旨在确定每篇文章中哪些词语被赋予了更高的权重。调查结果表明，假新闻的一个共同特征是对影响文章可信度的词语的关注度提高，虽然所占比例很小。为了评估模型的通用性，我们将在一个数据集上训练的模型应用于其他数据集的分类。结果表明，由于训练数据的独特性，准确率明显下降。这些观察结果表明，使用微调 BERT 模型提取的假新闻共同特征是有限的。

{"title":"Analyzing common lexical features of fake news using multi-head attention weights","authors":"Mamoru Mimura , Takayuki Ishimaru","doi":"10.1016/j.iot.2024.101409","DOIUrl":"10.1016/j.iot.2024.101409","url":null,"abstract":"<div><div>Numerous approaches have been developed to identify fake news through machine learning; however, these methods are predominantly assessed using singular datasets specific to certain fields, leading to a scarcity of research on versatile models adaptable to a range of domains. This study evaluates the adaptability of a fake news detection model across diverse fields, employing three distinct datasets. Furthermore, the study leverages the multi-head attention feature of bidirectional encoder representations from transformers (BERT) to scrutinize the feature extraction process in the model. In our analysis, we focused on words that are commonly emphasized by machine learning in fake news detection. The dataset comprised 27,442 instances of genuine news and 28,359 instances of fabricated news, each distinctly labeled. To examine the focal words, we utilized multi-head attention, a component of BERT. This mechanism assigns greater weight to words that receive more attention. Our investigation aimed to identify which words were assigned higher weights in each article. The findings indicate that while representing a minor percentage, a common characteristic of fake news is the heightened attention to words that influence the credibility of the article. To assess the versatility of the model, we applied the model trained on one dataset to classify other datasets. The results demonstrate a notable decline in accuracy, attributable to the distinctive characteristics of the training data. These observations suggest that common features among fake news, which could be extracted using the fine-tuned BERT model, are limited.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"28 ","pages":"Article 101409"},"PeriodicalIF":6.0,"publicationDate":"2024-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142540364","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Powerful graph neural network for node classification of the IoT network 用于物联网网络节点分类的强大图神经网络

IF 6 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Internet of Things

Pub Date : 2024-10-24 DOI: 10.1016/j.iot.2024.101410

Mohammad Abrar Shakil Sejan , Md Habibur Rahman , Md Abdul Aziz , Rana Tabassum , Jung-In Baik , Hyoung-Kyu Song

Internet of Things (IoT) devices are increasingly used in various applications in our daily lives. The network structure for IoT is heterogeneous and can create a complex architecture depending on the application and geographical structure. To efficiently process the information within this diverse and complex relationship, a robust data structure is needed for network operations. Graph neural network (GNN) technology is emerging as a capable tool for predicting complex data structures, such as graphs. Graphs can be employed to mimic the structure of IoT network and process information from IoT nodes using GNN techniques. In this paper, our goal is to explore the effectiveness of GNN in performing the node classification task for a given IoT network. We have generated three different IoT networks with varying network sizes, number of nodes, and feature sizes. We then test 12 different GNN algorithms to evaluate their performance in IoT node classification. Each method is examined in detail to observe its training behavior, testing behavior, and resilience against noise. In addition, time complexity and generalization ability of each model have also been studied. The experimental results show that some methods exhibit high resilience against noisy data for IoT node classification accuracy.

物联网（IoT）设备越来越多地应用于我们日常生活中的各种应用。物联网的网络结构是异构的，根据应用和地理结构的不同，会形成一个复杂的架构。为了在这种多样而复杂的关系中高效处理信息，网络运行需要一个强大的数据结构。图神经网络（GNN）技术正在成为预测复杂数据结构（如图）的有效工具。图可以用来模仿物联网网络的结构，并利用 GNN 技术处理来自物联网节点的信息。在本文中，我们的目标是探索 GNN 在执行给定物联网网络节点分类任务时的有效性。我们生成了三个不同的物联网网络，其网络规模、节点数量和特征大小各不相同。然后，我们测试了 12 种不同的 GNN 算法，以评估它们在物联网节点分类中的性能。我们对每种方法都进行了详细研究，以观察其训练行为、测试行为和抗噪声能力。此外，还研究了每个模型的时间复杂性和泛化能力。实验结果表明，一些方法在提高物联网节点分类准确性方面表现出较高的抗噪声数据能力。

{"title":"Powerful graph neural network for node classification of the IoT network","authors":"Mohammad Abrar Shakil Sejan , Md Habibur Rahman , Md Abdul Aziz , Rana Tabassum , Jung-In Baik , Hyoung-Kyu Song","doi":"10.1016/j.iot.2024.101410","DOIUrl":"10.1016/j.iot.2024.101410","url":null,"abstract":"<div><div>Internet of Things (IoT) devices are increasingly used in various applications in our daily lives. The network structure for IoT is heterogeneous and can create a complex architecture depending on the application and geographical structure. To efficiently process the information within this diverse and complex relationship, a robust data structure is needed for network operations. Graph neural network (GNN) technology is emerging as a capable tool for predicting complex data structures, such as graphs. Graphs can be employed to mimic the structure of IoT network and process information from IoT nodes using GNN techniques. In this paper, our goal is to explore the effectiveness of GNN in performing the node classification task for a given IoT network. We have generated three different IoT networks with varying network sizes, number of nodes, and feature sizes. We then test 12 different GNN algorithms to evaluate their performance in IoT node classification. Each method is examined in detail to observe its training behavior, testing behavior, and resilience against noise. In addition, time complexity and generalization ability of each model have also been studied. The experimental results show that some methods exhibit high resilience against noisy data for IoT node classification accuracy.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"28 ","pages":"Article 101410"},"PeriodicalIF":6.0,"publicationDate":"2024-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142572179","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Fuzzy-based task offloading in Internet of Vehicles (IoV) edge computing for latency-sensitive applications 车联网 (IoV) 边缘计算中基于模糊的任务卸载，适用于延迟敏感型应用

IF 6 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Internet of Things

Pub Date : 2024-10-24 DOI: 10.1016/j.iot.2024.101392

Zouheir Trabelsi , Muhammad Ali , Tariq Qayyum

As vehicular applications continue to evolve, the computational capabilities of individual vehicles alone are no longer sufficient to meet the increasing demands. This has led to the integration of edge computing in the Internet of Vehicles (IoV) as an essential solution. Due to the limited resources within vehicles, there is often a need to offload tasks to edge nodes. However, task offloading in IoV environments presents several challenges, including high mobility, dynamic network topology, and varying node density. Traditional offloading methods fail to effectively address these challenges. Moreover, tasks differ in importance, necessitating a mechanism for edge nodes to prioritize tasks based on their urgency. To overcome these challenges, we propose a Vehicle-to-Vehicle (V2V) fuzzy-based task offloading scheme. In this scheme, fuzzy logic plays a critical role by enabling dynamic prioritization of tasks based on their urgency and the available computational resources at edge nodes, ensuring intelligent, context-aware decision-making. The user vehicle selects an appropriate edge node using an edge selection mechanism, which guarantees prolonged connection time and sufficient computational resources. Tasks at the edge are then organized based on their latency requirements and evaluated using a fuzzy rule-based inference system. Our simulation results demonstrate improved task execution rates, reduced overall system delay, and minimized queuing delays.

随着车辆应用的不断发展，仅靠单个车辆的计算能力已不足以满足日益增长的需求。因此，将边缘计算集成到车联网（IoV）中成为一种重要的解决方案。由于车辆内部资源有限，通常需要将任务卸载到边缘节点。然而，IoV 环境中的任务卸载面临着一些挑战，包括高流动性、动态网络拓扑和不同的节点密度。传统的卸载方法无法有效应对这些挑战。此外，任务的重要性各不相同，因此边缘节点需要一种机制来根据任务的紧迫性确定优先级。为了克服这些挑战，我们提出了一种基于模糊逻辑的车对车（V2V）任务卸载方案。在这一方案中，模糊逻辑起着关键作用，它能根据任务的紧迫性和边缘节点的可用计算资源动态地确定任务的优先级，确保做出智能的、能感知上下文的决策。用户车辆通过边缘选择机制选择合适的边缘节点，以保证较长的连接时间和充足的计算资源。然后根据延迟要求组织边缘任务，并使用基于模糊规则的推理系统进行评估。我们的模拟结果表明，任务执行率得到了提高，整体系统延迟减少，排队延迟降到了最低。

{"title":"Fuzzy-based task offloading in Internet of Vehicles (IoV) edge computing for latency-sensitive applications","authors":"Zouheir Trabelsi , Muhammad Ali , Tariq Qayyum","doi":"10.1016/j.iot.2024.101392","DOIUrl":"10.1016/j.iot.2024.101392","url":null,"abstract":"<div><div>As vehicular applications continue to evolve, the computational capabilities of individual vehicles alone are no longer sufficient to meet the increasing demands. This has led to the integration of edge computing in the Internet of Vehicles (IoV) as an essential solution. Due to the limited resources within vehicles, there is often a need to offload tasks to edge nodes. However, task offloading in IoV environments presents several challenges, including high mobility, dynamic network topology, and varying node density. Traditional offloading methods fail to effectively address these challenges. Moreover, tasks differ in importance, necessitating a mechanism for edge nodes to prioritize tasks based on their urgency. To overcome these challenges, we propose a Vehicle-to-Vehicle (V2V) fuzzy-based task offloading scheme. In this scheme, fuzzy logic plays a critical role by enabling dynamic prioritization of tasks based on their urgency and the available computational resources at edge nodes, ensuring intelligent, context-aware decision-making. The user vehicle selects an appropriate edge node using an edge selection mechanism, which guarantees prolonged connection time and sufficient computational resources. Tasks at the edge are then organized based on their latency requirements and evaluated using a fuzzy rule-based inference system. Our simulation results demonstrate improved task execution rates, reduced overall system delay, and minimized queuing delays.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"28 ","pages":"Article 101392"},"PeriodicalIF":6.0,"publicationDate":"2024-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142577837","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A combination learning framework to uncover cyber attacks in IoT networks 揭示物联网网络攻击的组合学习框架

IF 6 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Internet of Things

Pub Date : 2024-10-23 DOI: 10.1016/j.iot.2024.101395

Arati Behera , Kshira Sagar Sahoo , Tapas Kumar Mishra , Monowar Bhuyan

The Internet of Things (IoT) is rapidly expanding, connecting an increasing number of devices daily. Having diverse and extensive networking and resource-constrained devices creates vulnerabilities to various cyber-attacks. The IoT with the supervision of Software Defined Network (SDN) enhances the network performance through its flexibility and adaptability. Different methods have been employed for detecting security attacks; however, they are often computationally efficient and unsuitable for such resource-constraint environments. Consequently, there is a significant requirement to develop efficient security measures against a range of attacks. Recent advancements in deep learning (DL) models have paved the way for designing effective attack detection methods. In this study, we leverage Genetic Algorithm (GA) with a correlation coefficient as a fitness function for feature selection. Additionally, mutual information (MI) is applied for feature ranking to measure their dependency on the target variable. The selected optimal features were used to train a hybrid DNN model to uncover attacks in IoT networks. The hybrid DNN integrates Convolutional Neural Network, Bi-Gated Recurrent Units (Bi-GRU), and Bidirectional Long Short-Term Memory (Bi-LSTM) for training the input data. The performance of our proposed model is evaluated against several other baseline DL models, and an ablation study is provided. Three key datasets InSDN, UNSW-NB15, and CICIoT 2023 datasets, containing various types of attacks, were used to assess the performance of the model. The proposed model demonstrates an impressive accuracy and detection time over the existing model with lower resource consumption.

物联网（IoT）正在迅速发展，每天连接的设备数量越来越多。多样化、广泛的网络和资源有限的设备容易受到各种网络攻击。在软件定义网络（SDN）的监控下，物联网通过其灵活性和适应性提高了网络性能。人们采用了不同的方法来检测安全攻击，但这些方法往往计算效率低下，不适合这种资源受限的环境。因此，有必要开发高效的安全措施来应对一系列攻击。深度学习（DL）模型的最新进展为设计有效的攻击检测方法铺平了道路。在本研究中，我们利用遗传算法（GA），将相关系数作为特征选择的适应度函数。此外，互信息（MI）也被用于特征排序，以衡量它们对目标变量的依赖性。选定的最佳特征被用于训练混合 DNN 模型，以揭示物联网网络中的攻击。混合 DNN 集成了卷积神经网络、双向门控递归单元（Bi-GRU）和双向长短期记忆（Bi-LSTM），用于训练输入数据。对照其他几个基准 DL 模型，对我们提出的模型进行了性能评估，并提供了一项消融研究。三个关键数据集 InSDN、UNSW-NB15 和 CICIoT 2023 数据集包含各种类型的攻击，用于评估模型的性能。与现有模型相比，所提出的模型具有更高的准确性和更短的检测时间，而且资源消耗更少。

{"title":"A combination learning framework to uncover cyber attacks in IoT networks","authors":"Arati Behera , Kshira Sagar Sahoo , Tapas Kumar Mishra , Monowar Bhuyan","doi":"10.1016/j.iot.2024.101395","DOIUrl":"10.1016/j.iot.2024.101395","url":null,"abstract":"<div><div>The Internet of Things (IoT) is rapidly expanding, connecting an increasing number of devices daily. Having diverse and extensive networking and resource-constrained devices creates vulnerabilities to various cyber-attacks. The IoT with the supervision of Software Defined Network (SDN) enhances the network performance through its flexibility and adaptability. Different methods have been employed for detecting security attacks; however, they are often computationally efficient and unsuitable for such resource-constraint environments. Consequently, there is a significant requirement to develop efficient security measures against a range of attacks. Recent advancements in deep learning (DL) models have paved the way for designing effective attack detection methods. In this study, we leverage Genetic Algorithm (GA) with a correlation coefficient as a fitness function for feature selection. Additionally, mutual information (MI) is applied for feature ranking to measure their dependency on the target variable. The selected optimal features were used to train a hybrid DNN model to uncover attacks in IoT networks. The hybrid DNN integrates Convolutional Neural Network, Bi-Gated Recurrent Units (Bi-GRU), and Bidirectional Long Short-Term Memory (Bi-LSTM) for training the input data. The performance of our proposed model is evaluated against several other baseline DL models, and an ablation study is provided. Three key datasets InSDN, UNSW-NB15, and CICIoT 2023 datasets, containing various types of attacks, were used to assess the performance of the model. The proposed model demonstrates an impressive accuracy and detection time over the existing model with lower resource consumption.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"28 ","pages":"Article 101395"},"PeriodicalIF":6.0,"publicationDate":"2024-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142553076","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0