Internet of Things最新文献

Mitigating smart contract vulnerabilities in electronic toll collection using blockchain security 利用区块链安全缓解电子收费中的智能合约漏洞

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

Internet of Things

Pub Date : 2024-11-14 DOI: 10.1016/j.iot.2024.101429

Olfa Ben Rhaiem , Marwa Amara , Radhia Zaghdoud , Lamia Chaari , Maha Metab

The Internet of Vehicles (IOV) is a distributed network that provides several services based on vehicle information (e.g., location, speed), such as Electronic Toll Collection (ETC). ETC has been introduced to replace traditional toll booths, where vehicles need to line up to pay, especially during peak travel times. The main advantage of ETC is improved traffic efficiency. However, existing ETC systems often fail to secure the privacy of vehicle information and are vulnerable to fund theft. This makes automatic payments inefficient and susceptible to attacks like the Reentrancy attack.

In this paper, we leverage the Ethereum blockchain and smart contracts to facilitate automatic payments within the ETC system. The primary challenges addressed include authenticating vehicle data, automatically deducting fees from users’ wallets, and safeguarding against Reentrancy attacks in smart contracts, all while maintaining the confidentiality of distance-related information necessary for fee calculation. To address these concerns, we implement a decentralized application featuring a comprehensive end-to-end verification algorithm that operates at both entry and exit toll points, incorporating robust measures to protect sensitive distance data from potential leaks.

Results show that the accuracy of fees remains relatively high, with reasonable execution times. Additionally, our system’s gas consumption is more efficient compared to related works, making transactions more cost-effective. These outcomes demonstrate that the proposed system not only secures transactions but also ensures correct and efficient payment services, positioning it as a viable solution for improving the security and functionality of ETC systems.

车辆互联网（IOV）是一个分布式网络，可根据车辆信息（如位置、速度）提供多种服务，如电子收费（ETC）。ETC 的推出是为了取代传统的收费站，因为传统的收费站需要车辆排队缴费，尤其是在交通高峰期。ETC 的主要优点是提高交通效率。然而，现有的 ETC 系统往往无法确保车辆信息的私密性，而且容易发生资金被盗的情况。在本文中，我们利用以太坊区块链和智能合约来促进 ETC 系统内的自动支付。解决的主要挑战包括验证车辆数据、自动从用户钱包中扣除费用、防范智能合约中的重入攻击，同时保持费用计算所需的距离相关信息的机密性。为了解决这些问题，我们实施了一个去中心化的应用程序，该应用程序采用了一种全面的端到端验证算法，可在入口和出口收费点同时运行，并采用了稳健的措施来保护敏感的距离数据免遭潜在泄漏。此外，与相关研究相比，我们系统的气体消耗效率更高，使交易更具成本效益。这些结果表明，建议的系统不仅能确保交易安全，还能确保正确、高效的支付服务，是提高 ETC 系统安全性和功能性的可行解决方案。

{"title":"Mitigating smart contract vulnerabilities in electronic toll collection using blockchain security","authors":"Olfa Ben Rhaiem , Marwa Amara , Radhia Zaghdoud , Lamia Chaari , Maha Metab","doi":"10.1016/j.iot.2024.101429","DOIUrl":"10.1016/j.iot.2024.101429","url":null,"abstract":"<div><div>The Internet of Vehicles (IOV) is a distributed network that provides several services based on vehicle information (e.g., location, speed), such as Electronic Toll Collection (ETC). ETC has been introduced to replace traditional toll booths, where vehicles need to line up to pay, especially during peak travel times. The main advantage of ETC is improved traffic efficiency. However, existing ETC systems often fail to secure the privacy of vehicle information and are vulnerable to fund theft. This makes automatic payments inefficient and susceptible to attacks like the Reentrancy attack.</div><div>In this paper, we leverage the Ethereum blockchain and smart contracts to facilitate automatic payments within the ETC system. The primary challenges addressed include authenticating vehicle data, automatically deducting fees from users’ wallets, and safeguarding against Reentrancy attacks in smart contracts, all while maintaining the confidentiality of distance-related information necessary for fee calculation. To address these concerns, we implement a decentralized application featuring a comprehensive end-to-end verification algorithm that operates at both entry and exit toll points, incorporating robust measures to protect sensitive distance data from potential leaks.</div><div>Results show that the accuracy of fees remains relatively high, with reasonable execution times. Additionally, our system’s gas consumption is more efficient compared to related works, making transactions more cost-effective. These outcomes demonstrate that the proposed system not only secures transactions but also ensures correct and efficient payment services, positioning it as a viable solution for improving the security and functionality of ETC systems.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"28 ","pages":"Article 101429"},"PeriodicalIF":6.0,"publicationDate":"2024-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142654836","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

LBTMA: An integrated P4-enabled framework for optimized traffic management in SD-IoT networks LBTMA：用于优化 SD-IoT 网络流量管理的 P4 功能集成框架

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

Internet of Things

Pub Date : 2024-11-13 DOI: 10.1016/j.iot.2024.101432

Ameer El-Sayed , Wael Said , Amr Tolba , Yasser Alginahi , Ahmed A. Toony

This research introduces LBTMA, a novel framework for effective traffic management in Internet of Things (IoT) networks employing software-defined networking (SDN). LBTMA comprises three modules: P4-enabled Stateful Traffic Monitoring (P4-STM), P4-enabled Distributed Load Balancing (P4-DLBS), and P4-enabled Distributed Packet Aggregation and Disaggregation (P4-DPADS). Operating entirely within the data plane, the three modules collaboratively address the challenges of managing high communication traffic from IoT devices. P4-STM utilizes state tables for flow monitoring and anonymization, while introducing a novel multi-controller communication scheme (MCCS) that separates routine data from critical alerts through two dedicated channels. MCCS demonstrated a 25% improvement in throughput and a 51% decrease in latency compared to single controller architecture. P4-DLBS features Enhanced Weighted Round Robin (P4-EWRR) load balancing algorithm, which leverages P4′s distributed decision-making capabilities and inter-switch coordination for enhanced scalability and reduced controller burden. P4-EWRR continuously adjusts server weights based on real-time factors (e.g., queue length, server resource pool, CPU utilization) to ensure efficient resource allocation. In testing, P4-EWRR achieved an average response time of 15 ms and an average packet drop rate of 2%. P4-DPADS employs a hierarchical data plane to efficiently handle high volumes of small IoT packets. It demonstrated an average disaggregation accuracy of 98%, communication overhead reduction rate of 70%, and an impressive average aggregation ratio of 95%. Additionally, P4-DPADS contributes to a 25% reduction in latency and a 40% increase in throughput. The LBTMA framework's modularity and P4 programmability provide flexible, scalable, and efficient traffic management in IoT networks.

本研究介绍了 LBTMA，这是一种在采用软件定义网络（SDN）的物联网（IoT）网络中进行有效流量管理的新型框架。LBTMA 由三个模块组成：支持 P4 的状态流量监控（P4-STM）、支持 P4 的分布式负载平衡（P4-DLBS）和支持 P4 的分布式数据包聚合和分解（P4-DPADS）。这三个模块完全在数据平面内运行，共同应对管理来自物联网设备的高通信流量的挑战。P4-STM 利用状态表进行流量监控和匿名化，同时引入了新颖的多控制器通信方案（MCCS），通过两个专用通道将常规数据与关键警报分开。与单控制器架构相比，MCCS 的吞吐量提高了 25%，延迟降低了 51%。P4-DLBS 采用增强型加权轮循（P4-EWRR）负载平衡算法，该算法利用 P4 的分布式决策能力和交换机间协调能力，增强了可扩展性并减轻了控制器的负担。P4-EWRR 根据实时因素（如队列长度、服务器资源池、CPU 利用率）不断调整服务器权重，以确保高效的资源分配。在测试中，P4-EWRR 的平均响应时间为 15 毫秒，平均丢包率为 2%。P4-DPADS 采用分层数据平面，可有效处理大量小型物联网数据包。它的平均分解准确率达到 98%，通信开销减少率达到 70%，平均聚合率达到 95%，令人印象深刻。此外，P4-DPADS 还将延迟降低了 25%，吞吐量提高了 40%。LBTMA 框架的模块化和 P4 可编程性为物联网网络提供了灵活、可扩展和高效的流量管理。

{"title":"LBTMA: An integrated P4-enabled framework for optimized traffic management in SD-IoT networks","authors":"Ameer El-Sayed , Wael Said , Amr Tolba , Yasser Alginahi , Ahmed A. Toony","doi":"10.1016/j.iot.2024.101432","DOIUrl":"10.1016/j.iot.2024.101432","url":null,"abstract":"<div><div>This research introduces LBTMA, a novel framework for effective traffic management in Internet of Things (IoT) networks employing software-defined networking (SDN). LBTMA comprises three modules: P4-enabled Stateful Traffic Monitoring (P4-STM), P4-enabled Distributed Load Balancing (P4-DLBS), and P4-enabled Distributed Packet Aggregation and Disaggregation (P4-DPADS). Operating entirely within the data plane, the three modules collaboratively address the challenges of managing high communication traffic from IoT devices. P4-STM utilizes state tables for flow monitoring and anonymization, while introducing a novel multi-controller communication scheme (MCCS) that separates routine data from critical alerts through two dedicated channels. MCCS demonstrated a 25% improvement in throughput and a 51% decrease in latency compared to single controller architecture. P4-DLBS features Enhanced Weighted Round Robin (P4-EWRR) load balancing algorithm, which leverages P4′s distributed decision-making capabilities and inter-switch coordination for enhanced scalability and reduced controller burden. P4-EWRR continuously adjusts server weights based on real-time factors (e.g., queue length, server resource pool, CPU utilization) to ensure efficient resource allocation. In testing, P4-EWRR achieved an average response time of 15 ms and an average packet drop rate of 2%. P4-DPADS employs a hierarchical data plane to efficiently handle high volumes of small IoT packets. It demonstrated an average disaggregation accuracy of 98%, communication overhead reduction rate of 70%, and an impressive average aggregation ratio of 95%. Additionally, P4-DPADS contributes to a 25% reduction in latency and a 40% increase in throughput. The LBTMA framework's modularity and P4 programmability provide flexible, scalable, and efficient traffic management in IoT networks.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"28 ","pages":"Article 101432"},"PeriodicalIF":6.0,"publicationDate":"2024-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142654837","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

AI-based autonomous UAV swarm system for weed detection and treatment: Enhancing organic orange orchard efficiency with agriculture 5.0 基于人工智能的自主无人机群系统用于杂草检测和处理：利用农业 5.0 提高有机橘园效率

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

Internet of Things

Pub Date : 2024-11-12 DOI: 10.1016/j.iot.2024.101418

Paula Catala-Roman , Jaume Segura-Garcia , Esther Dura , Enrique A. Navarro-Camba , Jose M. Alcaraz-Calero , Miguel Garcia-Pineda

Weeds significantly threaten agricultural productivity by competing with crops for nutrients, particularly in organic farming, where chemical herbicides are prohibited. On Spain’s Mediterranean coast, organic citrus farms face increasing challenges from invasive species like Araujia sericifera and Cortaderia selloana, which further complicate cover crop management. This study introduces a swarm system of unmanned aerial vehicles (UAVs) equipped with neural networks based on YOLOv10 for the detection and geo-location of these invasive weeds. The system achieves F1-scores of 0.78 for Araujia sericifera and 0.80 for Cortaderia selloana. Using GPS and RTK, the UAVs generate KML files to guide diffuser drones for precise, localized treatments with organic products. By automating the detection, treatment, and elimination of invasive species, the system enhances both productivity and sustainability in organic farming. Additionally, the proposed solution addresses the high labor costs associated with manual weeding by reducing the need for human intervention. A comprehensive economic analysis indicates potential savings ranging from 1810 to 2650 € per hectare, depending on farm size. This innovative approach not only improves weed control efficiency but also promotes environmental sustainability, offering a scalable solution for organic and conventional agriculture alike.

杂草与作物争夺养分，严重威胁农业生产率，尤其是在禁止使用化学除草剂的有机农业中。在西班牙地中海沿岸，有机柑橘农场面临着 Araujia sericifera 和 Cortaderia selloana 等入侵物种带来的日益严峻的挑战，这使得覆盖作物管理变得更加复杂。本研究介绍了一种配备基于 YOLOv10 神经网络的无人机群系统，用于检测这些入侵杂草并进行地理定位。该系统对 Araujia sericifera 和 Cortaderia selloana 的 F1 分数分别为 0.78 和 0.80。无人机利用 GPS 和 RTK 生成 KML 文件，引导无人机使用有机产品进行精确的局部处理。通过自动检测、处理和消灭入侵物种，该系统提高了有机农业的生产率和可持续性。此外，拟议的解决方案还能减少人工干预，从而解决人工除草带来的高昂劳动力成本。综合经济分析表明，根据农场规模，每公顷可节省 1810 至 2650 欧元。这种创新方法不仅提高了除草效率，还促进了环境的可持续发展，为有机农业和传统农业提供了可扩展的解决方案。

{"title":"AI-based autonomous UAV swarm system for weed detection and treatment: Enhancing organic orange orchard efficiency with agriculture 5.0","authors":"Paula Catala-Roman , Jaume Segura-Garcia , Esther Dura , Enrique A. Navarro-Camba , Jose M. Alcaraz-Calero , Miguel Garcia-Pineda","doi":"10.1016/j.iot.2024.101418","DOIUrl":"10.1016/j.iot.2024.101418","url":null,"abstract":"<div><div>Weeds significantly threaten agricultural productivity by competing with crops for nutrients, particularly in organic farming, where chemical herbicides are prohibited. On Spain’s Mediterranean coast, organic citrus farms face increasing challenges from invasive species like <em>Araujia sericifera</em> and <em>Cortaderia selloana</em>, which further complicate cover crop management. This study introduces a swarm system of unmanned aerial vehicles (UAVs) equipped with neural networks based on YOLOv10 for the detection and geo-location of these invasive weeds. The system achieves F1-scores of 0.78 for <em>Araujia sericifera</em> and 0.80 for <em>Cortaderia selloana</em>. Using GPS and RTK, the UAVs generate KML files to guide diffuser drones for precise, localized treatments with organic products. By automating the detection, treatment, and elimination of invasive species, the system enhances both productivity and sustainability in organic farming. Additionally, the proposed solution addresses the high labor costs associated with manual weeding by reducing the need for human intervention. A comprehensive economic analysis indicates potential savings ranging from 1810 to 2650 € per hectare, depending on farm size. This innovative approach not only improves weed control efficiency but also promotes environmental sustainability, offering a scalable solution for organic and conventional agriculture alike.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"28 ","pages":"Article 101418"},"PeriodicalIF":6.0,"publicationDate":"2024-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142654834","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 consortium blockchain-edge enabled authentication scheme for underwater acoustic network (UAN) 用于水下声学网络 (UAN) 的联盟区块链边缘认证方案

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

Internet of Things

Pub Date : 2024-11-09 DOI: 10.1016/j.iot.2024.101426

Neeraj Kumar, Rifaqat Ali

The Internet of Things (IoT) allows for automated operations in diverse fields, such as agriculture monitoring, pollution monitoring, health care, and underwater monitoring. The Internet of Underwater Things (IoUT) observes the underwater environment, assists in exploration, mitigates disasters, and monitors some factors including temperature, pressure, and pollution. The IoUT relies on a network of intelligent underwater sensors that send data to surface base stations and IoT devices for storage and analysis. Nevertheless, these systems face security risks as they operate in unattended environments. Many authentication methods depend on a centralized third party, leading to higher computation costs and energy usage. To mitigate security risks, autonomous underwater devices need secure connections and authentication. This paper suggests a decentralized authentication mechanism for UAN to safeguard against unauthorized access and ensure secure data storage in the cloud. The proposed mechanism prioritizes robustness, transparency, and energy efficiency. The suggested solution incorporates an architecture based on edge and cloud layers, utilizing customized blockchain technology for secure storage and processing of data. The security of the proposed solution has been thoroughly examined through formal analysis utilizing the Real or Random (ROR) Oracle model and Scyther tool. Informal analysis further confirms the solution’s resilience against various malicious attacks. Additionally, performance and comparative analysis demonstrate that the proposed solution surpasses existing schemes.

物联网（IoT）可在农业监测、污染监测、医疗保健和水下监测等不同领域实现自动化操作。水下物联网（IoUT）可观测水下环境，协助勘探，减轻灾害，并监测温度、压力和污染等因素。IoUT 依靠智能水下传感器网络将数据发送到地面基站和物联网设备进行存储和分析。然而，这些系统在无人值守的环境中运行时面临着安全风险。许多身份验证方法依赖于集中的第三方，导致计算成本和能耗增加。为了降低安全风险，自主水下设备需要安全连接和认证。本文提出了一种用于 UAN 的分散式身份验证机制，以防止未经授权的访问并确保云中数据的安全存储。建议的机制优先考虑稳健性、透明度和能效。建议的解决方案采用基于边缘和云层的架构，利用定制的区块链技术实现数据的安全存储和处理。通过利用真实或随机（ROR）甲骨文模型和 Scyther 工具进行形式分析，对所建议解决方案的安全性进行了彻底检查。非正式分析进一步证实了该解决方案能够抵御各种恶意攻击。此外，性能和比较分析表明，拟议解决方案超越了现有方案。

{"title":"A consortium blockchain-edge enabled authentication scheme for underwater acoustic network (UAN)","authors":"Neeraj Kumar, Rifaqat Ali","doi":"10.1016/j.iot.2024.101426","DOIUrl":"10.1016/j.iot.2024.101426","url":null,"abstract":"<div><div>The Internet of Things (IoT) allows for automated operations in diverse fields, such as agriculture monitoring, pollution monitoring, health care, and underwater monitoring. The Internet of Underwater Things (IoUT) observes the underwater environment, assists in exploration, mitigates disasters, and monitors some factors including temperature, pressure, and pollution. The IoUT relies on a network of intelligent underwater sensors that send data to surface base stations and IoT devices for storage and analysis. Nevertheless, these systems face security risks as they operate in unattended environments. Many authentication methods depend on a centralized third party, leading to higher computation costs and energy usage. To mitigate security risks, autonomous underwater devices need secure connections and authentication. This paper suggests a decentralized authentication mechanism for UAN to safeguard against unauthorized access and ensure secure data storage in the cloud. The proposed mechanism prioritizes robustness, transparency, and energy efficiency. The suggested solution incorporates an architecture based on edge and cloud layers, utilizing customized blockchain technology for secure storage and processing of data. The security of the proposed solution has been thoroughly examined through formal analysis utilizing the Real or Random (ROR) Oracle model and Scyther tool. Informal analysis further confirms the solution’s resilience against various malicious attacks. Additionally, performance and comparative analysis demonstrate that the proposed solution surpasses existing schemes.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"28 ","pages":"Article 101426"},"PeriodicalIF":6.0,"publicationDate":"2024-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142654833","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

Is artificial intelligence a new battleground for cybersecurity? 人工智能是网络安全的新战场吗？

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

Internet of Things

Pub Date : 2024-11-06 DOI: 10.1016/j.iot.2024.101428

Khalid Khan , Adnan Khurshid , Javier Cifuentes-Faura

This study investigates the relationship between artificial intelligence and cybersecurity in the context of geopolitical risk. The findings from the full sample indicate that there is no correlation between artificial intelligence and cybersecurity. On the other hand, the outcomes demonstrate that artificial intelligence has a significant effect on cybersecurity and vice versa for the subsamples driven by increased automation, the sophistication of cyberattacks that outpace defensive capabilities, state-sponsored threats, and tensions between global powers. These results confirm the bidirectional relationship between artificial intelligence and cybersecurity across different subsamples, which coincides with greater geopolitical tension. The results align with the diffusion of the innovation model, which states that geopolitics can influence the adoption and impact of AI innovations in cybersecurity. Therefore, the AI-cybersecurity relationship requires balanced innovation and security policies.

本研究调查了地缘政治风险背景下人工智能与网络安全之间的关系。全样本的研究结果表明，人工智能与网络安全之间不存在相关性。另一方面，研究结果表明，在自动化程度提高、网络攻击的复杂程度超过防御能力、国家支持的威胁以及全球大国之间的紧张关系等因素的驱动下，人工智能对网络安全有显著影响，反之亦然。这些结果证实了不同子样本中人工智能与网络安全之间的双向关系，这与地缘政治紧张局势的加剧不谋而合。这些结果符合创新扩散模型，即地缘政治会影响网络安全领域人工智能创新的采用和影响。因此，人工智能与网络安全的关系需要平衡的创新和安全政策。

引用次数: 0

Exploring the ALNS method for improved cybersecurity: A deep learning approach for attack detection in IoT and IIoT environments 探索 ALNS 方法，提高网络安全：物联网和 IIoT 环境中攻击检测的深度学习方法

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

Internet of Things

Pub Date : 2024-11-06 DOI: 10.1016/j.iot.2024.101421

Sarra Cherfi , Ammar Boulaiche , Ali Lemouari

With the emergence of the Internet of Things (IoT) and the Industrial Internet of Things (IIoT), the flow of data across the world is experiencing a rapid expansion. Unfortunately, this exponential growth is accompanied by a proportional increase in cyber threats, jeopardizing the security and integrity of computer systems. In this context, intrusion detection becomes a necessity to protect networks and systems against potential attacks, ensuring their proper functioning and reliability. In this paper, we propose a deep learning-based model for attack detection. This model utilizes a convolutional neural network to train the datasets, which are first cleaned and preprocessed. The model inputs are selected using an optimization method called adaptive large neighborhood search. The results obtained for the four datasets used – CICIDS2017, Edge-IIoTset, ToN-IoT windows7, and ToN-IoT windows10 – demonstrate the model’s effectiveness for both multi-class and binary classification cases. In the binary case, the accuracy reaches 99.85%, 100%, 99.97%, and 100%, respectively, and in the multi-class case, it stands at 99.81%, 94.98%, 99.92%, and 99.84%, respectively.

随着物联网（IoT）和工业物联网（IIoT）的出现，全球的数据流正在经历快速扩张。不幸的是，这种指数式增长伴随着网络威胁的成比例增加，危及计算机系统的安全性和完整性。在这种情况下，入侵检测成为保护网络和系统免受潜在攻击、确保其正常运行和可靠性的必要手段。在本文中，我们提出了一种基于深度学习的攻击检测模型。该模型利用卷积神经网络来训练数据集，首先对数据集进行清理和预处理。模型输入的选择采用了一种称为自适应大邻域搜索的优化方法。所使用的四个数据集（CICIDS2017、Edge-IIoTset、ToN-IoT windows7 和 ToN-IoT windows10）的结果表明，该模型在多类和二元分类情况下都很有效。在二元情况下，准确率分别达到 99.85%、100%、99.97% 和 100%；在多类情况下，准确率分别达到 99.81%、94.98%、99.92% 和 99.84%。

{"title":"Exploring the ALNS method for improved cybersecurity: A deep learning approach for attack detection in IoT and IIoT environments","authors":"Sarra Cherfi , Ammar Boulaiche , Ali Lemouari","doi":"10.1016/j.iot.2024.101421","DOIUrl":"10.1016/j.iot.2024.101421","url":null,"abstract":"<div><div>With the emergence of the Internet of Things (IoT) and the Industrial Internet of Things (IIoT), the flow of data across the world is experiencing a rapid expansion. Unfortunately, this exponential growth is accompanied by a proportional increase in cyber threats, jeopardizing the security and integrity of computer systems. In this context, intrusion detection becomes a necessity to protect networks and systems against potential attacks, ensuring their proper functioning and reliability. In this paper, we propose a deep learning-based model for attack detection. This model utilizes a convolutional neural network to train the datasets, which are first cleaned and preprocessed. The model inputs are selected using an optimization method called adaptive large neighborhood search. The results obtained for the four datasets used – CICIDS2017, Edge-IIoTset, ToN-IoT windows7, and ToN-IoT windows10 – demonstrate the model’s effectiveness for both multi-class and binary classification cases. In the binary case, the accuracy reaches 99.85%, 100%, 99.97%, and 100%, respectively, and in the multi-class case, it stands at 99.81%, 94.98%, 99.92%, and 99.84%, respectively.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"28 ","pages":"Article 101421"},"PeriodicalIF":6.0,"publicationDate":"2024-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142654832","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

Ensuring patient safety in IoMT: A systematic literature review of behavior-based intrusion detection systems 确保物联网技术中的患者安全：基于行为的入侵检测系统的系统文献综述

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

Internet of Things

Pub Date : 2024-11-05 DOI: 10.1016/j.iot.2024.101420

Jordi Doménech , Isabel V. Martin-Faus , Saber Mhiri , Josep Pegueroles

Integrating Internet of Medical Things (IoMT) devices into healthcare has enhanced patient care, enabling real-time data exchange and remote monitoring, yet it also presents substantial security risks. Addressing these risks requires robust Intrusion Detection Systems (IDS). While existing studies target this topic, a systematic literature review focused on the current state and advancements in Behavior-based Intrusion Detection Systems for IoMT environments is necessary. This systematic literature review analyzes 81 studies from the past five years, answering three key research questions: (1) What are the Behavior-based IDS currently used in healthcare? (2) How do the detected attacks impact patient safety? (3) Do these IDS include prevention measures? The findings indicate that nearly 84% of the reviewed studies utilize Artificial Intelligence (AI) techniques for threat detection. However, significant challenges persist, such as the scarcity of IoMT-specific datasets, limited focus on patient safety, and the absence of comprehensive prevention and mitigation strategies. This review highlights the need for more robust, patient-centric security solutions. In particular, developing IoMT-specific datasets and enhancing defensive mechanisms are essential to meet the unique security requirements of IoMT environments.

将医疗物联网 (IoMT) 设备集成到医疗保健中，可实现实时数据交换和远程监控，从而加强对患者的护理，但同时也带来了巨大的安全风险。应对这些风险需要强大的入侵检测系统（IDS）。虽然现有的研究都针对这一主题，但有必要进行一次系统的文献综述，重点研究 IoMT 环境中基于行为的入侵检测系统的现状和进展。本系统性文献综述分析了过去五年中的 81 项研究，回答了三个关键研究问题：（1）目前在医疗保健领域使用的基于行为的入侵检测系统有哪些？(2）检测到的攻击对患者安全有何影响？(3) 这些 IDS 是否包括预防措施？研究结果表明，近 84% 的综述研究利用人工智能 (AI) 技术进行威胁检测。然而，重大挑战依然存在，如缺乏针对物联网医疗的数据集、对患者安全的关注有限以及缺乏全面的预防和缓解策略。本综述强调需要更强大的、以患者为中心的安全解决方案。特别是，开发物联网医疗专用数据集和加强防御机制对于满足物联网医疗环境的独特安全要求至关重要。

{"title":"Ensuring patient safety in IoMT: A systematic literature review of behavior-based intrusion detection systems","authors":"Jordi Doménech , Isabel V. Martin-Faus , Saber Mhiri , Josep Pegueroles","doi":"10.1016/j.iot.2024.101420","DOIUrl":"10.1016/j.iot.2024.101420","url":null,"abstract":"<div><div>Integrating Internet of Medical Things (IoMT) devices into healthcare has enhanced patient care, enabling real-time data exchange and remote monitoring, yet it also presents substantial security risks. Addressing these risks requires robust Intrusion Detection Systems (IDS). While existing studies target this topic, a systematic literature review focused on the current state and advancements in Behavior-based Intrusion Detection Systems for IoMT environments is necessary. This systematic literature review analyzes 81 studies from the past five years, answering three key research questions: (1) What are the Behavior-based IDS currently used in healthcare? (2) How do the detected attacks impact patient safety? (3) Do these IDS include prevention measures? The findings indicate that nearly 84% of the reviewed studies utilize Artificial Intelligence (AI) techniques for threat detection. However, significant challenges persist, such as the scarcity of IoMT-specific datasets, limited focus on patient safety, and the absence of comprehensive prevention and mitigation strategies. This review highlights the need for more robust, patient-centric security solutions. In particular, developing IoMT-specific datasets and enhancing defensive mechanisms are essential to meet the unique security requirements of IoMT environments.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"28 ","pages":"Article 101420"},"PeriodicalIF":6.0,"publicationDate":"2024-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142654968","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

Reinforcement learning-based drone-assisted collection system for infection samples in IoT environment 基于强化学习的无人机辅助物联网环境感染样本采集系统

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

Internet of Things

Pub Date : 2024-11-02 DOI: 10.1016/j.iot.2024.101407

Xiuwen Fu , Shengqi Kang

Since infectious disease surveillance and control rely on efficient sample collection, it is important to research the infection sample collection system. The combination of Internet of Things (IoT) and drone technology provides an emerging solution to this issue. This paper designs a drone-assisted collection system for infection samples (DASS) that provides safe, intelligent, and efficient sample collection services. In this system, flexible collector drones gather infection samples from remote users and return to designated transit points to unload. Meanwhile, deliverer drones shuttle between the testing center and transit points, transporting all packaged infection samples to the testing center. However, the moment when users post collection requests is unknown. This dynamism and uncertainty present new challenges for the routing and scheduling of heterogeneous drones. To address this issue, this paper proposes a deep reinforcement learning-based dynamic sample collection (RLDSC) scheme. Considering the differences in infection samples, minimizing age of samples (AoS) is introduced as an objective. Simulation results indicate that the RLDSC scheme outperforms existing solutions in both effectiveness and efficiency.

由于传染病监测和控制依赖于高效的样本采集，因此研究传染病样本采集系统非常重要。物联网（IoT）与无人机技术的结合为这一问题提供了一种新兴的解决方案。本文设计了一种无人机辅助感染样本采集系统（DASS），可提供安全、智能、高效的样本采集服务。在该系统中，灵活的采集器无人机从远程用户处采集感染样本，并返回指定中转站卸载。同时，运送无人机穿梭于检测中心和中转点之间，将所有包装好的感染样本运送到检测中心。然而，用户发出采集请求的时刻是未知的。这种动态性和不确定性给异构无人机的路由和调度带来了新的挑战。为解决这一问题，本文提出了一种基于深度强化学习的动态样本采集（RLDSC）方案。考虑到感染样本的差异，引入了最小化样本年龄（AoS）作为目标。仿真结果表明，RLDSC 方案在效果和效率上都优于现有解决方案。

{"title":"Reinforcement learning-based drone-assisted collection system for infection samples in IoT environment","authors":"Xiuwen Fu , Shengqi Kang","doi":"10.1016/j.iot.2024.101407","DOIUrl":"10.1016/j.iot.2024.101407","url":null,"abstract":"<div><div>Since infectious disease surveillance and control rely on efficient sample collection, it is important to research the infection sample collection system. The combination of Internet of Things (IoT) and drone technology provides an emerging solution to this issue. This paper designs a drone-assisted collection system for infection samples (DASS) that provides safe, intelligent, and efficient sample collection services. In this system, flexible collector drones gather infection samples from remote users and return to designated transit points to unload. Meanwhile, deliverer drones shuttle between the testing center and transit points, transporting all packaged infection samples to the testing center. However, the moment when users post collection requests is unknown. This dynamism and uncertainty present new challenges for the routing and scheduling of heterogeneous drones. To address this issue, this paper proposes a deep reinforcement learning-based dynamic sample collection (RLDSC) scheme. Considering the differences in infection samples, minimizing age of samples (AoS) is introduced as an objective. Simulation results indicate that the RLDSC scheme outperforms existing solutions in both effectiveness and efficiency.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"28 ","pages":"Article 101407"},"PeriodicalIF":6.0,"publicationDate":"2024-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142654969","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

Internet-of-Mirrors (IoM) for connected healthcare and beauty: A prospective vision 用于联网医疗和美容的镜联网（IoM）：前景展望

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.2024.101415

Haneen Fatima, Muhammad Ali Imran, Ahmad Taha, Lina Mohjazi

With the shift towards smart objects and automated services in many industries, the health and beauty industries are also becoming increasingly involved in AI-driven smart systems. There is a rising market demand for personalised services and a need for unified platforms in many sectors, specifically the cosmetics and healthcare industries. Alongside this rising demand, there are two major gaps when considering the integration of autonomous systems within these sectors. Firstly, the existing smart systems in the cosmetics industry are limited to single-purpose products and the employed technologies are not widespread enough to support the growing consumer demand for personalisation. Secondly, despite the rise of smart devices in healthcare, the current state-of-the-art services do not fulfil the accessibility demands and holistic nature of healthcare. To bridge these gaps, we propose integrating autonomous systems with health and beauty services through a unified visual platform coined as the Internet-of-Mirrors (IoM), an interconnected system of smart mirrors with sensing and communication capabilities where the smart mirror functions as an immersive visual dashboard to provide personalised services for health and beauty consultations and routines. We aim to present an overview of current state-of-the-art technologies that will enable the development of the IoM as well as provide a practical vision of this system with innovative scenarios to give a forward-looking vision for assistive technologies. We also discuss the missing capabilities and challenges the development of the IoM would face and outline future research directions that will support the realisation of our proposed framework.

随着许多行业向智能物品和自动化服务转变，健康和美容行业也越来越多地涉足人工智能驱动的智能系统。市场对个性化服务的需求不断增长，许多行业都需要统一的平台，特别是化妆品和医疗保健行业。在需求不断增长的同时，这些行业在考虑整合自主系统时还存在两大差距。首先，化妆品行业现有的智能系统仅限于单一用途的产品，所采用的技术也不够广泛，不足以支持消费者日益增长的个性化需求。其次，尽管智能设备在医疗保健领域兴起，但目前最先进的服务并不能满足医疗保健的无障碍需求和整体性。为了弥补这些差距，我们建议通过一个统一的视觉平台将自主系统与健康和美容服务整合在一起，该平台被称为镜联网（IoM），是一个由具有传感和通信功能的智能镜子组成的互联系统，其中智能镜子的功能是作为一个沉浸式视觉仪表板，为健康和美容咨询及日常活动提供个性化服务。我们的目标是概述当前最先进的技术，这些技术将促进物联网的发展，并通过创新方案提供该系统的实用愿景，从而为辅助技术提供前瞻性愿景。我们还讨论了物联网发展所面临的能力缺失和挑战，并概述了未来的研究方向，以支持实现我们提出的框架。

{"title":"Internet-of-Mirrors (IoM) for connected healthcare and beauty: A prospective vision","authors":"Haneen Fatima, Muhammad Ali Imran, Ahmad Taha, Lina Mohjazi","doi":"10.1016/j.iot.2024.101415","DOIUrl":"10.1016/j.iot.2024.101415","url":null,"abstract":"<div><div>With the shift towards smart objects and automated services in many industries, the health and beauty industries are also becoming increasingly involved in AI-driven smart systems. There is a rising market demand for personalised services and a need for unified platforms in many sectors, specifically the cosmetics and healthcare industries. Alongside this rising demand, there are two major gaps when considering the integration of autonomous systems within these sectors. Firstly, the existing smart systems in the cosmetics industry are limited to single-purpose products and the employed technologies are not widespread enough to support the growing consumer demand for personalisation. Secondly, despite the rise of smart devices in healthcare, the current state-of-the-art services do not fulfil the accessibility demands and holistic nature of healthcare. To bridge these gaps, we propose integrating autonomous systems with health and beauty services through a unified visual platform coined as the Internet-of-Mirrors (IoM), an interconnected system of smart mirrors with sensing and communication capabilities where the smart mirror functions as an immersive visual dashboard to provide personalised services for health and beauty consultations and routines. We aim to present an overview of current state-of-the-art technologies that will enable the development of the IoM as well as provide a practical vision of this system with innovative scenarios to give a forward-looking vision for assistive technologies. We also discuss the missing capabilities and challenges the development of the IoM would face and outline future research directions that will support the realisation of our proposed framework.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"28 ","pages":"Article 101415"},"PeriodicalIF":6.0,"publicationDate":"2024-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142587376","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

Concept-drift-adaptive anomaly detector for marine sensor data streams 海洋传感器数据流的概念漂移自适应异常检测器

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.2024.101414

Ngoc-Thanh Nguyen , Rogardt Heldal , Patrizio Pelliccione

There is an increasing industry demand for reliable Anomaly Detection (AD) solutions to detect erroneous measurements or alarm events in marine sensor data. We evaluated 36 state-of-the-art AD algorithms published in the last three decades on our three real-world univariate time-series datasets collected from marine sensors. None of them achieved the accuracy expected from the marine industry. The algorithms are underperforming on our data because they are too generalized and cannot handle unforeseen data distribution changes, referred to as concept drift.

To address these issues, we developed a novel algorithm called AdapAD, which incorporates sensor design information into decision-making processes and can adapt to concept drift. We actively collaborated with nine domain experts from six marine organizations to ensure that AdapAD meets their needs. The experiments show that AdapAD satisfies the accuracy expectation and outperforms 40 existing AD algorithms. The decision-making time of AdapAD, measured on a commodity laptop, is generally less than one minute, showing its potential for application to perform real-time AD in marine sensor data streams. AdapAD was acknowledged as a viable solution for automatic marine data quality control and flood detection by 17 domain experts from 12 organizations. For transparency and to facilitate further research, we provide the implementation of AdapAD and the real-world marine sensor data used in the study.

业界对可靠的异常检测（AD）解决方案的需求与日俱增，以检测海洋传感器数据中的错误测量或警报事件。我们在从海洋传感器收集的三个真实世界单变量时间序列数据集上评估了过去三十年中发布的 36 种最先进的 AD 算法。结果发现，没有一种算法能达到海洋行业的预期精度。这些算法在我们的数据上表现不佳，因为它们过于泛化，无法处理不可预见的数据分布变化，即概念漂移。为了解决这些问题，我们开发了一种名为 AdapAD 的新型算法，它将传感器设计信息纳入决策过程，并能适应概念漂移。我们与来自六个海洋组织的九位领域专家积极合作，确保 AdapAD 满足他们的需求。实验结果表明，AdapAD 达到了预期精度，并优于 40 种现有的 AD 算法。在商用笔记本电脑上测量的 AdapAD 决策时间通常少于一分钟，这表明它具有在海洋传感器数据流中执行实时 AD 的应用潜力。来自 12 个组织的 17 位领域专家认为 AdapAD 是自动海洋数据质量控制和洪水探测的可行解决方案。为了提高透明度和促进进一步研究，我们提供了 AdapAD 的实现方法和研究中使用的真实世界海洋传感器数据。

{"title":"Concept-drift-adaptive anomaly detector for marine sensor data streams","authors":"Ngoc-Thanh Nguyen , Rogardt Heldal , Patrizio Pelliccione","doi":"10.1016/j.iot.2024.101414","DOIUrl":"10.1016/j.iot.2024.101414","url":null,"abstract":"<div><div>There is an increasing industry demand for reliable Anomaly Detection (AD) solutions to detect erroneous measurements or alarm events in marine sensor data. We evaluated 36 state-of-the-art AD algorithms published in the last three decades on our three real-world univariate time-series datasets collected from marine sensors. None of them achieved the accuracy expected from the marine industry. The algorithms are underperforming on our data because they are too generalized and cannot handle unforeseen data distribution changes, referred to as concept drift.</div><div>To address these issues, we developed a novel algorithm called <span>AdapAD</span>, which incorporates sensor design information into decision-making processes and can adapt to concept drift. We actively collaborated with nine domain experts from six marine organizations to ensure that <span>AdapAD</span> meets their needs. The experiments show that <span>AdapAD</span> satisfies the accuracy expectation and outperforms 40 existing AD algorithms. The decision-making time of <span>AdapAD</span>, measured on a commodity laptop, is generally less than one minute, showing its potential for application to perform real-time AD in marine sensor data streams. <span>AdapAD</span> was acknowledged as a viable solution for automatic marine data quality control and flood detection by 17 domain experts from 12 organizations. For transparency and to facilitate further research, we provide the implementation of <span>AdapAD</span> and the real-world marine sensor data used in the study.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"28 ","pages":"Article 101414"},"PeriodicalIF":6.0,"publicationDate":"2024-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142593944","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