Internet of Things and Cyber-Physical Systems最新文献

{"title":"Generative AI in cybersecurity: A comprehensive review of LLM applications and vulnerabilities","authors":"Mohamed Amine Ferrag ,&nbsp;Fatima Alwahedi ,&nbsp;Ammar Battah ,&nbsp;Bilel Cherif ,&nbsp;Abdechakour Mechri ,&nbsp;Norbert Tihanyi ,&nbsp;Tamas Bisztray ,&nbsp;Merouane Debbah","doi":"10.1016/j.iotcps.2025.01.001","DOIUrl":"10.1016/j.iotcps.2025.01.001","url":null,"abstract":"<div><div>This paper provides a comprehensive review of the future of cybersecurity through Generative AI and Large Language Models (LLMs). We explore LLM applications across various domains, including hardware design security, intrusion detection, software engineering, design verification, cyber threat intelligence, malware detection, and phishing detection. We present an overview of LLM evolution and its current state, focusing on advancements in models such as GPT-4, GPT-3.5, Mixtral-8x7B, BERT, Falcon2, and LLaMA. Our analysis extends to LLM vulnerabilities, such as prompt injection, insecure output handling, data poisoning, DDoS attacks, and adversarial instructions. We delve into mitigation strategies to protect these models, providing a comprehensive look at potential attack scenarios and prevention techniques. Furthermore, we evaluate the performance of 42 LLM models in cybersecurity knowledge and hardware security, highlighting their strengths and weaknesses. We thoroughly evaluate cybersecurity datasets for LLM training and testing, covering the lifecycle from data creation to usage and identifying gaps for future research. In addition, we review new strategies for leveraging LLMs, including techniques like Half-Quadratic Quantization (HQQ), Reinforcement Learning with Human Feedback (RLHF), Direct Preference Optimization (DPO), Quantized Low-Rank Adapters (QLoRA), and Retrieval-Augmented Generation (RAG). These insights aim to enhance real-time cybersecurity defenses and improve the sophistication of LLM applications in threat detection and response. Our paper provides a foundational understanding and strategic direction for integrating LLMs into future cybersecurity frameworks, emphasizing innovation and robust model deployment to safeguard against evolving cyber threats.</div></div>","PeriodicalId":100724,"journal":{"name":"Internet of Things and Cyber-Physical Systems","volume":"5 ","pages":"Pages 1-46"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143947102","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Trust management in the internet of everything: A review of deep-learning based solutions","authors":"Hind Bangui ,&nbsp;Mouzhi Ge ,&nbsp;Barbora Buhnova","doi":"10.1016/j.iotcps.2026.03.005","DOIUrl":"10.1016/j.iotcps.2026.03.005","url":null,"abstract":"<div><div>Internet of Everything (IoE) is an extension of Internet of Things (IoT) that has revolutionized the digitalization of our society by connecting things and humans to create a digital world. As a result, IoE has reshaped the way that humans and autonomous systems interact and exchange information in network connections. However, the digitization imposes new security, trust, and safety concerns, such as the risk of undesirable behavior of driverless cars, which might cause dangerous road consequences. In this context, Deep-Learning (DL) applications have emerged in trust management to proactively improve the efficiency, reliability, security, trust, and safety of different IoE entities, and then achieve the sustainability of different social IoE relationships. To support further progress in integrating DL-based solutions in trust management, this paper reviews the existing literature related to DL-based trust management. Specifically, the review targets the DL-based approaches employed in trust management, their components and application areas in the context of IoE, and trust relationships in IoE. Furthermore, it highlights a set of research challenges, opportunities and recommendations related to the adoption of proactive trust management using deep learning in IoE.</div></div>","PeriodicalId":100724,"journal":{"name":"Internet of Things and Cyber-Physical Systems","volume":"5 ","pages":"Pages 210-231"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147538042","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"LoRa for multihop communication in internet of underground things under fading environments","authors":"Irfana Ilyas Jameela Manzil ,&nbsp;Ruhul Amin Khalil ,&nbsp;Nasir Saeed","doi":"10.1016/j.iotcps.2025.05.001","DOIUrl":"10.1016/j.iotcps.2025.05.001","url":null,"abstract":"<div><div>This paper investigates the suitability of LoRa wireless technology for reliable underground-to-aboveground communication in the context of sustainable agricultural monitoring. We comprehensively analyze LoRa's performance in single-hop and multi-hop scenarios, considering complex environmental conditions and path loss. Mathematical expressions for the bit error rate (BER) are derived under both additive white Gaussian noise (AWGN) and Rayleigh fading, including multi-hop networks with decode-and-forward relays. Simulations under realistic Rayleigh fading scenarios validate our theoretical models. Our findings demonstrate that multi-hop LoRa networks significantly outperform single-hop systems in challenging underground environments, underscoring LoRa's potential for enhancing sustainability in various subterranean Internet of Underground Things (IoUT) agricultural applications.</div></div>","PeriodicalId":100724,"journal":{"name":"Internet of Things and Cyber-Physical Systems","volume":"5 ","pages":"Pages 87-94"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144205480","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"AOA-SMA-EGRUAttNet: A hybrid feature selection and dual-stream attention-based intrusion detection framework for IIoT systems","authors":"Yousef Sanjalawe ,&nbsp;Salam Fraihat ,&nbsp;Salam Al-E'mari ,&nbsp;Sharif Naser Makhadmeh","doi":"10.1016/j.iotcps.2026.03.002","DOIUrl":"10.1016/j.iotcps.2026.03.002","url":null,"abstract":"<div><div>The rapid expansion of the Industrial Internet of Things (IIoT) has introduced unprecedented opportunities for smart industrial automation. Yet, it also exposes critical systems to various sophisticated cyber threats. Traditional Intrusion Detection Systems (IDS) often struggle with the complexity, heterogeneity, and class imbalance inherent in IIoT environments, leading to high false alarm rates and suboptimal generalization. This paper addresses these limitations by proposing a novel hybrid intrusion detection framework, AOA-SMA-EGRUAttNet, that unites advanced feature selection and dual-stream deep learning to enhance detection accuracy and interpretability. The core motivation is to improve the computational efficiency and classification robustness of IDS models through targeted dimensionality reduction and context-aware temporal learning. The framework integrates the Archimedes Optimization Algorithm (AOA) and Slime Mould Algorithm (SMA) for hybrid feature selection, optimizing subsets based on classification relevance, redundancy, and processing cost. Selected features are fed into the Enhanced GRU-Attention Network (E-GRUAttNet), a lightweight dual-stream model combining gated recurrent units and parallel attention mechanisms. Experimental evaluation across four benchmark IIoT datasets: CICAPT-IIoT, Edge-IIoTset, X-IIoTID, and WUSTL-IIoT-2021, demonstrates that the proposed method consistently outperforms state-of-the-art baselines in accuracy (up to 98.9%) and macro-F1 score, while achieving over 55% feature reduction. Ablation studies and statistical analyses confirm the significance and robustness of each component. This paper contributes a scalable and interpretable IDS architecture that meets the evolving demands of industrial cybersecurity, providing a strong foundation for future adaptive detection systems in critical infrastructures.</div></div>","PeriodicalId":100724,"journal":{"name":"Internet of Things and Cyber-Physical Systems","volume":"5 ","pages":"Pages 143-164"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147449042","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"UMetaBE-DPPML: Urban metaverse & blockchain-enabled decentralised privacy-preserving machine learning verification and authentication with metaverse immersive devices","authors":"Kaya Kuru,&nbsp;Kaan Kuru","doi":"10.1016/j.iotcps.2025.02.001","DOIUrl":"10.1016/j.iotcps.2025.02.001","url":null,"abstract":"<div><div>It is anticipated that cybercrime activities will be widespread in the urban metaverse ecosystem due to its high economic value with new types of assets and its immersive nature with a variety of experiences. Ensuring reliable urban metaverse cyberspaces requires addressing two critical challenges, namely, cybersecurity and privacy protection. This study, by analysing potential cyberthreats in the urban metaverse cyberspaces, proposes a blockchain-based Decentralised Privacy-Preserving Machine Learning (DPPML) authentication and verification methodology, which uses the metaverse immersive devices and can be instrumented effectively against identity impersonation and theft of credentials, identity, or avatars. Blockchain technology and Federated Learning (FL) are merged in the developed DPPML approach not only to eliminate the requirement of a trusted third party for the verification of the authenticity of transactions and immersive actions, but also, to avoid Single Point of Failure (SPoF) and Generative Adversarial Networks (GAN) attacks by detecting malicious nodes. The developed methodology has been tested using Motion Capture Suits (MoCaps) in a co-simulation environment with the Proof-of-Work (PoW) consensus mechanism. The preliminary results suggest that the built techniques in the DPPML approach can prevent unreal transactions, impersonation, identity theft, and theft of credentials or avatars promptly before any transactions have been executed or immersive experiences have been shared with others. The proposed system will be tested with a larger number of nodes involving the Proof-of-Stake (PoS) consensus mechanism using several other metaverse immersive devices as a future job.</div></div>","PeriodicalId":100724,"journal":{"name":"Internet of Things and Cyber-Physical Systems","volume":"5 ","pages":"Pages 47-86"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144099446","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Advanced Machine Learning in Smart Grids: An overview","authors":"Hassan N. Noura ,&nbsp;Jean Paul A. Yaacoub ,&nbsp;Ola Salman ,&nbsp;Ali Chehab","doi":"10.1016/j.iotcps.2025.05.002","DOIUrl":"10.1016/j.iotcps.2025.05.002","url":null,"abstract":"<div><div>Adopting Advanced Machine Learning for Smart Grids (ML-SG) is a promising strategy that revolutionizes the energy industry to optimize energy usage, improve grid management, and foster sustainability. It also increases the efficiency, reliability, and sustainability of contemporary power systems. Furthermore, incorporating machine learning into smart grids has important practical ramifications and can help address some of the most pressing issues facing contemporary energy systems. By precisely forecasting consumption trends and facilitating dynamic pricing models that take into account current grid circumstances, Machine Learning (ML) can improve demand response tactics. Additionally, it is essential for preserving grid stability since it can promptly identify irregularities and react to system oscillations, preventing blackouts and equipment failures. Furthermore, through supply and demand balance, energy dispatch optimization, and solar and wind power forecasts, ML makes it easier to seamlessly integrate renewable energy sources. These characteristics facilitate the shift to a more robust, adaptable, and ecologically friendly energy infrastructure in addition to increasing operating efficiency. In this paper, we investigate the development of ML solutions that benefit from the enormous amounts of data generated by IoT devices in the smart grid. Furthermore, this study examines the benefits and drawbacks of the adoption of ML-SG and offers an outline of their use while highlighting the implications of integrating ML into smart grids. In addition, it explores and analyzes how ML algorithms can be used for load forecasting and enabling accurate and real-time decision making in smart grids. The objective of this work is to analyze smart grid operations at different levels, such as predicting energy demand, identifying abnormalities, and reducing cybersecurity threats by using sophisticated ML-based algorithms, especially discussing attacks and countermeasures against these ML models. This work concludes with suggestions and recommendations that highlight the importance of improving the security and accuracy of ML-SG, while shedding some light on future directions. In the future, this work aims to contribute to the development of efficient ML solutions for energy infrastructure to become more effective and sustainable, by discussing data science and ML issues related to smart grids.</div></div>","PeriodicalId":100724,"journal":{"name":"Internet of Things and Cyber-Physical Systems","volume":"5 ","pages":"Pages 95-142"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144205481","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Blockchain and NFT-based digital passports for UAV preoperational certification","authors":"Abduraouf Hassan ,&nbsp;Ahmad Musamih ,&nbsp;Khaled Salah ,&nbsp;Ernesto Damiani ,&nbsp;Mohammed Omar ,&nbsp;Dragan Boscovic ,&nbsp;Ibrar Yaqoob","doi":"10.1016/j.iotcps.2026.03.003","DOIUrl":"10.1016/j.iotcps.2026.03.003","url":null,"abstract":"<div><div>Digital passports for Unmanned Aerial Vehicles (UAVs) are used to create a unified system for tracking and identifying UAVs, which ensures compliance and security. A digital passport holds details like the owner's information, drone model, and activity history, thereby enabling easy tracking and identification of UAVs. However, the absence of decentralized and secure digital passport management systems for UAVs makes it challenging to ensure tamper-proof records and transparent ownership verification across borders. This paper proposes a proof of concept for a decentralized blockchain and Non-Fungible Tokens (NFTs)-based digital passport to improve the transparency, traceability, trust, and security of UAV preoperational certifications. The proposed solution secures UAVs' preoperational stages such as design, manufacturing, and distribution, integrating best practices from the Federal Aviation Administration (FAA) and the European Union Aviation Safety Agency (EASA) for standardized compliance. The proposed NFT-based digital passport consolidates certification records into a single verifiable document, providing access to compliance history. Four smart contracts are developed to enforce role-based access control, and off-chain decentralized storage using the InterPlanetary File System (IPFS) is employed to manage large UAV records. Evaluation through implementation and testing demonstrates the solution's effectiveness in managing UAV certification workflows and enforcing regulatory compliance. Security analysis shows robustness against unauthorized modifications and common vulnerabilities, while cost analysis assesses deployment viability across multiple blockchain networks. A comparison of the proposed solution with existing UAV compliance and certification frameworks shows that it effectively fills the gap by addressing preoperational certification. The smart contract code is publicly available on GitHub.</div></div>","PeriodicalId":100724,"journal":{"name":"Internet of Things and Cyber-Physical Systems","volume":"5 ","pages":"Pages 165-184"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147537862","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A review on LLMs for IoT ecosystem: State-of-the-art, lightweight models, use cases, key challenges, future directions","authors":"Partha Pratim Ray","doi":"10.1016/j.iotcps.2026.04.002","DOIUrl":"10.1016/j.iotcps.2026.04.002","url":null,"abstract":"<div><div>The emergence of Large Language Models (LLMs) has profoundly reshaped computational linguistics, enabling unprecedented reasoning, context awareness, and semantic understanding capabilities. Integrating these sophisticated models into Internet-of-Things (IoT) ecosystems holds transformative potential for enabling intelligent, autonomous, and contextually-aware applications. This article begins with an extensive state-of-the-art survey of existing literature on the integration of LLMs within IoT environments, establishing foundational insights into current capabilities, limitations, and deployment frameworks. Subsequently, the manuscript contributes a comprehensive analysis of lightweight LLMs and embedding models suitable for resource-constrained IoT platforms while introducing a taxonomy of sub-billion–parameter (&lt;1B), mid-range (1B–2B), and exact 2B–parameter LLMs—spanning families such as Qwen, Llama, SmolLM, and IBM's Granite—as well as embedding models under 1B parameters optimized for low-latency retrieval. Comparative assessments elucidate trade-offs in model size, inference latency, context windows, energy consumption, and performance across models categorized by parameter count. Next, a diverse spectrum of prospective use cases—including home healthcare, smart agriculture, industrial optimization, and environmental monitoring—demonstrates the practical efficacy of deploying tailored LLM-IoT frameworks for real-world problem-solving. Later, the article systematically explores key challenges that must be addressed to fully realize the integration of LLMs within IoT contexts, encompassing resource constraints, heterogeneous data processing, privacy and security risks, latency requirements, model interpretability, and ethical considerations. Finally, we outline critical directions for future research, advocating advancements in IoT-specific model architectures, multimodal sensor fusion strategies, real-time adaptive inference methods, energy-aware inference scheduling, and privacy-preserving federated learning paradigms.</div></div>","PeriodicalId":100724,"journal":{"name":"Internet of Things and Cyber-Physical Systems","volume":"5 ","pages":"Pages 275-328"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147739942","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Intelligence analytics in industry 4.0: IoT-based oil and gas industry","authors":"Yasin Ranjbar,&nbsp;Arash Nemati","doi":"10.1016/j.iotcps.2026.03.004","DOIUrl":"10.1016/j.iotcps.2026.03.004","url":null,"abstract":"<div><div>The smart Oil and Gas Industry (OGI) is a transformation of the corresponding automated industry via using Industry 4.0 (I4.0) enablers, including Internet of Things (IoTs), cloud computing, blockchain, big data analytics, robotics, simulation, 3D printing, augmented reality/virtual reality, system integration, and cybersecurity. IoTs facilitate and accelerate real-time data gathering using proper sensors in any conditions and then transmit the collected data set to cloud servers via the internet. This paper contributes to assessing the OGI adaptation to IoT-based management by proposing an assessment framework involving assessment criteria and the corresponding hierarchical structure. In addition, the proposed framework includes the Analytical Hierarchy Process (AHP) to derive the significance of criteria and sub-criteria based on experts’ judgment. Results of employing this framework in a case study from Iran showed that the application of IoT in some sectors, such as pipeline and Health/Safety/Environment (HSE), is crucial, and in other sectors of OGI, like Exploration and production, is less significant, according to the questioned experts. In addition, emergency maintenance, monitoring pipeline parameters, real-time detection of dangerous conditions, and well automation are the most significant sub-criteria of maintenance, pipeline, HSE, and exploration and production, respectively.</div></div>","PeriodicalId":100724,"journal":{"name":"Internet of Things and Cyber-Physical Systems","volume":"5 ","pages":"Pages 262-274"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147740076","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Review of Generative AI methods in cybersecurity","authors":"Yagmur Yigit ,&nbsp;William J. Buchanan ,&nbsp;Madjid G. Tehrani ,&nbsp;Leandros Maglaras","doi":"10.1016/j.iotcps.2026.04.001","DOIUrl":"10.1016/j.iotcps.2026.04.001","url":null,"abstract":"<div><div>Over the last decade, Artificial Intelligence (AI) has become increasingly popular, especially with the use of chatbots such as ChatGPT, Google's Gemini, and DALL-E. With this rise, large language models (LLMs) and Generative AI (GenAI) have also become more prevalent in everyday use. These advancements strengthen cybersecurity's defensive posture and open up new attack avenues for adversaries as well. This paper provides a comprehensive overview of the current state-of-the-art deployments of GenAI, covering assaults, jailbreaking, and applications of prompt injection and reverse psychology. This paper also provides the various applications of GenAI in cybercrimes, such as automated hacking, phishing emails, social engineering, reverse cryptography, creating attack payloads, and creating malware. GenAI can significantly improve the automation of defensive cybersecurity processes through strategies such as dataset construction, safe code development, threat intelligence, defensive measures, reporting, and cyberattack detection. In this study, we suggest that future research should focus on developing robust ethical norms and innovative defence mechanisms to address the current issues that GenAI creates and also further encourage an impartial approach to its future application in cybersecurity. Moreover, we underscore the importance of interdisciplinary approaches further to bridge the gap between scientific developments and ethical considerations.</div></div>","PeriodicalId":100724,"journal":{"name":"Internet of Things and Cyber-Physical Systems","volume":"5 ","pages":"Pages 241-261"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147650043","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}