Internet of Things最新文献_第10页

Incentivizing task offloading in IoT: A distributed auctions-based DRL approach

IF 6 3区计算机科学

Internet of Things Pub Date : 2025-01-12 DOI: 10.1016/j.iot.2025.101493

Soumeya Demil, Mohammed Riyadh Abdmeziem

{"title":"Incentivizing task offloading in IoT: A distributed auctions-based DRL approach","authors":"Soumeya Demil, Mohammed Riyadh Abdmeziem","doi":"10.1016/j.iot.2025.101493","DOIUrl":"10.1016/j.iot.2025.101493","url":null,"abstract":"<div><div>Federated Learning (FL) has emerged as a powerful tool for leveraging the vast quantities of data generated by Internet of Things (IoT) devices. Its advantage lies in its ability to preserve participants’ data privacy through keeping it local. In addition, FL alleviates the communication overhead in cloud-centric ML for IoT approaches, through sharing model updates instead of large raw data, which optimizes bandwidth use. Furthermore, decentralized FL has been useful in addressing security concerns typical in conventional settings. Nevertheless, in such zero-trust scenarios where there is no central coordinator, nodes exhibit reluctance to participate due to the lack of clear rewards and trust issues. Additionally, constrained FL clients may abandon their tasks, which negatively impacts learning performance. In this paper, we propose a double-incentive FL approach to address the dual challenge of node reluctance and task offloading in a fully distributed FL-based IoT network. We introduce an auction-based offloading scheme to handle task abandonment. Multi-Agent Deep Reinforcement Learning (MADRL) is leveraged to build a bidding strategy with long-term optimization of system and individual utilities. We also present a client filtering and rewarding algorithm based on a reputation model. Our objective is to promote truthfulness and enhance resilience against malicious nodes, while improving energy efficiency and accuracy. By employing a REINFORCE-based scheme for offloading, our approach demonstrates a superior trade-off between energy efficiency and accuracy, as well as resilience to malicious behavior. Furthermore, empirical results highlight its performance in terms of truthfulness, despite the uncertain and opaque nature of the environment.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"30 ","pages":"Article 101493"},"PeriodicalIF":6.0,"publicationDate":"2025-01-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143222960","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

Low latency and secure data encryption for multi-hop biometric authentication in distributed networks

IF 6 3区计算机科学

Internet of Things Pub Date : 2025-01-12 DOI: 10.1016/j.iot.2025.101501

Sun-Jin Lee, Jin-Min Lee, Il-Gu Lee

{"title":"Low latency and secure data encryption for multi-hop biometric authentication in distributed networks","authors":"Sun-Jin Lee, Jin-Min Lee, Il-Gu Lee","doi":"10.1016/j.iot.2025.101501","DOIUrl":"10.1016/j.iot.2025.101501","url":null,"abstract":"<div><div>Because of the rapid development of artificial intelligence and big data technology, biometric information has become widely used in applications across industries, such as biometric authentication and telemedicine. However, biometric information is unique and cannot be changed or restored once leaked. Therefore, the security and management of biometric information must be more thorough than those applied to other types of information. In particular, if end-to-end encryption is not maintained and decryption is performed for the sake of precise data learning or information protection at intermediate nodes, the security of the process becomes weaker, increasing the risk of data leakage. To solve such problems, research is currently being conducted on homomorphic encryption, in which calculation and learning can be performed in an encrypted state, for biometric recognition systems. However, homomorphic encryption requires a larger ciphertext size than those used in other encryption methods. Thus, this type of encryption has been limited by its large delay, which deteriorates the performance because of noise boost-up and thus does not guarantee quality of service in a multi-hop network environment. This study proposes a novel multi-hop encryption-based biometric information slicing method to improve latency and security in biometric authentication. Experimental results demonstrate an 83.23% latency reduction compared to a conventional single-process model in a Paillier-based homomorphic encryption environment. Additionally, it offers a 98.4% security improvement compared to the commonly used Advanced Encryption Standard for packet encryption. This approach effectively addresses the trade-off between security and latency, a critical aspect not fully explored in previous studies.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"30 ","pages":"Article 101501"},"PeriodicalIF":6.0,"publicationDate":"2025-01-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143222885","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

Privacy-preserved mutually-trusted 5G communications in presence of pervasive attacks

IF 6 3区计算机科学

Internet of Things Pub Date : 2025-01-11 DOI: 10.1016/j.iot.2025.101491

Yomna Ibrahim , Mai A. Abdel-Malek , Mohamed Azab , Mohamed RM Rizk

{"title":"Privacy-preserved mutually-trusted 5G communications in presence of pervasive attacks","authors":"Yomna Ibrahim , Mai A. Abdel-Malek , Mohamed Azab , Mohamed RM Rizk","doi":"10.1016/j.iot.2025.101491","DOIUrl":"10.1016/j.iot.2025.101491","url":null,"abstract":"<div><div>Ensuring secure fifth-generation (5G) cellular communications is crucial for protecting the privacy of Internet of Things (IoT) devices, especially wearables that can disclose sensitive information if the communication stream is compromised. Confidentiality must be maintained for personal health metrics, location data, and other private information transmitted over cellular networks. Users inherently trust cellular infrastructure protocols to deliver robust security. Therefore, the security provided by 5G networks is indispensable, as it mitigates cyber threats and ensures the integrity and confidentiality of data collected and transmitted by wearables and other IoT devices, thereby upholding user privacy in the increasingly connected IoT ecosystem. The 5G Authentication and Key Agreement (5G-AKA) protocol builds upon and enhances its fourth-generation (4G) predecessor to address and proactively mitigate inherited vulnerabilities. However, it still faces multiple vulnerabilities, primarily due to the lack of mutual authentication in the access and the unprotected signaling during the 5G-AKA procedure further increases exposure. This paper highlights vulnerabilities in the 5G-AKA protocol related to user privacy and data availability, particularly those emerging during bootstrapping and from unprotected messages within the AKA procedure. We propose security enhancements within the bootstrapping and 5G-AKA procedures to address the lack of authentication between the User Equipment (UE) and the Serving Network (SN) and to encapsulate unprotected messages within the 5G-AKA signaling. To demonstrate the effectiveness of our proposed security enhancements, we conduct both qualitative and formal security analyses. Furthermore, the proposed authentication algorithm is implemented as a part of a 5G-based communication simulation to investigate the increased computational and communication delays associated with the proposed security enhancements.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"30 ","pages":"Article 101491"},"PeriodicalIF":6.0,"publicationDate":"2025-01-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143222957","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

CNTNF framework focus on forecasting and verifying network threats and faults

IF 6 3区计算机科学

Internet of Things Pub Date : 2025-01-11 DOI: 10.1016/j.iot.2025.101504

Hsia-Hsiang Chen

{"title":"CNTNF framework focus on forecasting and verifying network threats and faults","authors":"Hsia-Hsiang Chen","doi":"10.1016/j.iot.2025.101504","DOIUrl":"10.1016/j.iot.2025.101504","url":null,"abstract":"<div><div>I propose two frameworks. One framework combines network threats and network faults (CNTNF). This framework incorporates our previous network threat detection and fault localization research. For previous works, I propose three models—the fast filtering and identification system using an ant agent system to effectively defend against denial of service (DoS), quality of service (QoS) attacks, and QoS fault cases, it is called the unified threat identification and fault localization by using ant colony optimization (ACO) (UTFACO), the ant colony system for distributed detection and identification of distributed denial of service (DDoS), namely the distributed detection and identification ant colony system (DDIACS) and the software fault localization (SFL)/network fault localization (NFL) cases are overcome by the spectrum-based SFL (SSFL) system architecture. Additionally, the CNTNF includes the SSFL method to diagnose network faults and multiple QoS fault cases. For this reason, I design a flexible framework, which can be expanded based on the new features when the threats or faults are found and outperformed. The second framework is for the comparison and analysis of the various countermeasures against threats and faults. I develop the attack and defense for forecast and verification modeling framework (ADFVMF). ADFVMF accelerates the development of CNTNF and assesses its contribution value. The experimental results demonstrate that the aggregate total average (ATAVG) of detection rate (DEC-R), ATAVG of accuracy rate (ACC-R), and ATAVG of duration time (DUR-T) are 84.26 %, 88.03 %, and 11.38 s, respectively. Consequently, CNTNF is a stability framework based on the boundary limitations and the optimization of parameters in terms of efficiency and effectiveness.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"30 ","pages":"Article 101504"},"PeriodicalIF":6.0,"publicationDate":"2025-01-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143223134","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

IoT-enhanced battery management system for real-time SoC and SoH monitoring using STM32-based programmable electronic load

IF 6 3区计算机科学

Internet of Things Pub Date : 2025-01-11 DOI: 10.1016/j.iot.2025.101509

Abdulkadir Gozuoglu

{"title":"IoT-enhanced battery management system for real-time SoC and SoH monitoring using STM32-based programmable electronic load","authors":"Abdulkadir Gozuoglu","doi":"10.1016/j.iot.2025.101509","DOIUrl":"10.1016/j.iot.2025.101509","url":null,"abstract":"<div><div>Electronic dummy loads (EDLs) are essential for characterizing the discharge behavior of batteries and power supplies. Accurate battery performance monitoring is critical for applications ranging from renewable energy storage to electric vehicles. This study presents the design and implementation of an advanced, low-cost EDL integrated with Internet of Things (IoT) capabilities using Espressif Systems Platform (ESP) -based microcontrollers, specifically the NodeMCU or ESP32. The primary objective is to monitor lithium-ion battery packages' state of charge (SoC) and state of health (SoH). The designed system maintains a constant current during discharge, ensuring precise capacity measurement despite the decreasing voltage levels of batteries. This feature is essential for accurately determining the battery's capacity and health status. The integration with IoT networks significantly enhances the functionality of the device. Using the ESP-based microcontroller, real-time voltage, current, and power data is transmitted to an online platform, allowing for remote monitoring and data logging. This capability not only improves the accessibility and usability of the system but also facilitates long-term data analysis and performance tracking. The developed dummy load system is versatile, supporting both single-cell batteries and multiple-cell configurations. The adjustable current selection property allows it to draw a constant current from batteries, making it suitable for various applications. Simulation and real-world application results demonstrate the system's effectiveness, providing reliable SoC and SoH information. Our results underscore the potential of integrating IoT technologies with battery monitoring systems, offering enhanced monitoring, improved accuracy, and the convenience of remote access. This innovative, cost-effective approach can significantly contribute to developing more intelligent and reliable battery-powered systems.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"30 ","pages":"Article 101509"},"PeriodicalIF":6.0,"publicationDate":"2025-01-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143223137","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

FedCLLM: Federated client selection assisted large language model utilizing domain description

IF 6 3区计算机科学

Internet of Things Pub Date : 2025-01-10 DOI: 10.1016/j.iot.2025.101506

Ignatius Iwan, Sean Yonathan Tanjung, Bernardo Nugroho Yahya, Seok-Lyong Lee

{"title":"FedCLLM: Federated client selection assisted large language model utilizing domain description","authors":"Ignatius Iwan, Sean Yonathan Tanjung, Bernardo Nugroho Yahya, Seok-Lyong Lee","doi":"10.1016/j.iot.2025.101506","DOIUrl":"10.1016/j.iot.2025.101506","url":null,"abstract":"<div><div>Federated Learning has become an emerging topic since the rise of privacy regulation regarding personal data protection and sensitivity. It provides a decentralized training approach to train a global model between a server and multiple clients while ensuring client data confidentiality. However, in practical scenarios, there are malicious clients within a large pool of client candidates, and selecting trustworthy honest clients becomes a crucial problem. Some previous works tried to solve the problem by exchanging client data for comparison and using a labelled dataset for evaluating client models to select honest clients. However, they pose a limitation when the server possesses unlabelled data from other sources and has limited or unavailable resources to label the data. To address the issue, this work proposes FedCLLM, a novel approach using Large Language Models (LLM) proficiency in semantic tasks on text-based data to compare client and server domain descriptions summary in a text format and assess their similarity. Experiments on popular benchmark datasets show that FedCLLM effectively distinguishes honest clients from potentially malicious ones and outperforms other previous works in terms of performance.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"30 ","pages":"Article 101506"},"PeriodicalIF":6.0,"publicationDate":"2025-01-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143222924","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

Photoplethysmography signals and physiological data in feature engineering and machine learning algorithms to calculate human-obesity-related indices

IF 6 3区计算机科学

Internet of Things Pub Date : 2025-01-10 DOI: 10.1016/j.iot.2025.101503

Chih-Ta Yen, Chia-Hsang Chang, Jung-Ren Wong

{"title":"Photoplethysmography signals and physiological data in feature engineering and machine learning algorithms to calculate human-obesity-related indices","authors":"Chih-Ta Yen, Chia-Hsang Chang, Jung-Ren Wong","doi":"10.1016/j.iot.2025.101503","DOIUrl":"10.1016/j.iot.2025.101503","url":null,"abstract":"<div><div>The study developed a method based on photoplethysmography (PPG) and machine learning algorithms to predict three human-obesity-related indices: body mass index (BMI), visceral adipose tissue (VAT), and subcutaneous adipose tissue (SAT). This method eliminates the need for conventional, complex medical imaging examinations, such as computed tomography scans or magnetic resonance imaging. These conventional methods are not only time-consuming and expensive but computed tomography scans may also result in unnecessary radiation exposure to the body. PPG-based technology enables easy measurements without the need for complicated examination and measurement processes. In the proposed method, PPG signals are recorded and then processed to obtain statistical features, such as mean and variance. Subsequently, the measured data and extracted features are used in machine learning algorithms to predict human-obesity-related indices. Several feature engineering methods were employed to enhance the accuracy of our method, with the mean absolute errors for BMI, VAT, and SAT estimates decreasing from 0.419 to 0.228, from 0.624 to 0.563, and from 2.092 to 0.500, respectively. The results of the study indicate that combining PPG technology with machine learning and feature engineering methods is a convenient and effective method for measuring human-obesity-related indices. The information obtained through this method can enable individuals to understand their health status and adopt suitable measures for health management and disease prevention.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"30 ","pages":"Article 101503"},"PeriodicalIF":6.0,"publicationDate":"2025-01-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143222923","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

Tiny keys hold big secrets: On efficiency of Pairing-Based Cryptography in IoT

IF 6 3区计算机科学

Internet of Things Pub Date : 2025-01-09 DOI: 10.1016/j.iot.2025.101489

Pericle Perazzo, Carlo Vallati

{"title":"Tiny keys hold big secrets: On efficiency of Pairing-Based Cryptography in IoT","authors":"Pericle Perazzo, Carlo Vallati","doi":"10.1016/j.iot.2025.101489","DOIUrl":"10.1016/j.iot.2025.101489","url":null,"abstract":"<div><div>Pairing-Based Cryptography (PBC) is a sub-field of elliptic curve cryptography that has been used to design ingenious security protocols including Short Signatures (SS), Identity-Based Encryption (IBE), and Attribute-Based Encryption (ABE). These protocols have extremely promising applications in diverse scenarios, including Internet of Things (IoT), which usually involves computing devices with limited processing, memory, and energy capabilities. Many studies in the literature evaluated the performance of PBC on typical IoT devices, giving promising results, and showing that a large class of constrained devices can run PBC schemes. However, in the last years, new advancements in Number Field Sieve algorithms threatened the security of PBC, so that all protocols must be re-parametrized with larger keys to maintain the same security level as before. Therefore, past literature reporting PBC performance on IoT devices must be redone because optimistic, and it is not clear whether present IoT devices will bear PBC. In this paper we evaluate the performance of some prominent PBC schemes on a very constrained device, namely the Zolertia RE-Mote platform, which is equipped with an ARM Cortex-M3 processor. From our experiments, the usage of IBE and SS schemes is still possible on IoT devices, but the security level is limited to 80 or 100 bits. Reaching greater security levels leads to higher execution times, which might not be compatible with many IoT applications. The usage of ABE is efficient only with IoT-oriented schemes, which offer good performance at the cost of a limited policy expressiveness.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"30 ","pages":"Article 101489"},"PeriodicalIF":6.0,"publicationDate":"2025-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143222959","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

Intelligent human activity recognition for healthcare digital twin

IF 6 3区计算机科学

Internet of Things Pub Date : 2025-01-09 DOI: 10.1016/j.iot.2025.101497

Elif Bozkaya-Aras , Tolga Onel , Levent Eriskin , Mumtaz Karatas

{"title":"Intelligent human activity recognition for healthcare digital twin","authors":"Elif Bozkaya-Aras , Tolga Onel , Levent Eriskin , Mumtaz Karatas","doi":"10.1016/j.iot.2025.101497","DOIUrl":"10.1016/j.iot.2025.101497","url":null,"abstract":"<div><div>Human activity recognition and healthcare monitoring are becoming increasingly popular as cost-effective and innovative solutions to improve the standard of healthcare in the era of Industry 4.0. The concept of the Internet of Healthcare Things (IoHT) supports these solutions and builds a virtualized and software-controlled infrastructure. This new approach leads to the development of new concepts by digitalizing and connecting everything. Despite the significant advancements in IoHT, there are still challenges in processing vast amounts of data and handling resource-limited devices. In this regard, digital twin technology is an emerging tool to enhance IoHT services. With the help of digital twin, data processing at the edge devices can effectively overcome these challenges by reducing data transfer limitations and latency while improving prediction accuracy. In this paper, we present an intelligent human activity recognition framework in healthcare digital twin services. Our framework creates digital twins of wearable and portable devices/sensors in the physical network, collects real-time and historical data, and applies advanced analytics for feedback. The main contributions of this paper are: (<em>i</em>) We propose a novel four-layer digital twin architecture framework for human activity recognition. (<em>ii</em>) We discuss how the layered architecture and data processing at the edge devices enhance decision-making and classification accuracy. It is also aimed to design an environment where data with different characteristics, priorities, and transmission timings (i.e., regularly transmitted and critical) are comprised so that we can measure the same state through multiple sensors to improve system performance. (<em>iii</em>) We develop an Artificial Neural Network (ANN) based model and evaluate the proposed digital twin-assisted model using two different datasets. The results show the benefits of the proposed digital twin-assisted framework, providing feedback to individuals.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"30 ","pages":"Article 101497"},"PeriodicalIF":6.0,"publicationDate":"2025-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143222958","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

HYRIDE: HYbrid and Robust Intrusion DEtection approach for enhancing cybersecurity in Industry 4.0

IF 6 3区计算机科学

Internet of Things Pub Date : 2025-01-07 DOI: 10.1016/j.iot.2025.101492

Shubham Srivastav , Amit K. Shukla , Sandeep Kumar , Pranab K. Muhuri

{"title":"HYRIDE: HYbrid and Robust Intrusion DEtection approach for enhancing cybersecurity in Industry 4.0","authors":"Shubham Srivastav , Amit K. Shukla , Sandeep Kumar , Pranab K. Muhuri","doi":"10.1016/j.iot.2025.101492","DOIUrl":"10.1016/j.iot.2025.101492","url":null,"abstract":"<div><div>The interconnectedness and smartness aspect between several components of Industry 4.0 has caused sudden increase in data and its exchange, which has resulted in significant cybersecurity challenges. Thus, a better threat intelligence technique is required for monitoring and identifying malicious cyberattacks. However, distinguishing between a normal event and a cyberattack can be difficult because label information is mostly unavailable. Therefore, it is imperative to develop a threat intelligence system that operates more effectively without supervision, i.e., without a label. Additionally, reducing the false positive rate in cyber threat detection is a more promising step for a safer and more reliable environment. Also, the enormous number of features in the data for intrusion detection tasks sometimes results in significant computing costs. Therefore, a novel hybrid feature selection based unsupervised intrusion detection system is proposed, which is termed as HYbrid and Robust Intrusion DEtection (HYRIDE), that uses a wide variety of feature selection techniques to obtain the fewest, best possible features. The local outlier factor, elliptic envelope, and histogram-based outlier score models are then trained using these features to identify threats in network traffic automatically. As a result, HYRIDE can effectively and efficiently distinguish between normal events and intrusions. The proposed methodology is empirically evaluated using popular datasets such as Telemetry datasets of Internet of Things (IoT) services, Operating systems datasets of Windows and Linux, as well as datasets of Network traffic (TON_IoT), University of New South Wales-Network Benchmark (UNSW-NB15), and Canadian Institute of Cybersecurity Intrusion Detection System (CICIDS 2017).</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"30 ","pages":"Article 101492"},"PeriodicalIF":6.0,"publicationDate":"2025-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143222925","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