Andy Reed, Laurence Dooley, Soraya Kouadri Mostefaoui
{"title":"SA-IDS: A single attribute intrusion detection system for Slow DoS attacks in IoT networks","authors":"Andy Reed, Laurence Dooley, Soraya Kouadri Mostefaoui","doi":"10.1016/j.iot.2025.101512","DOIUrl":"10.1016/j.iot.2025.101512","url":null,"abstract":"<div><div>Internet of Things (IoT) technologies are expanding and pervade evermore application domains bringing a raft of positive user benefits. However, the matter of application layer security and the omnipresent danger of Denial of Service (DoS) attacks remains a significant risk to effective IoT performance. DoS is especially serious in IoT networks given the propensity for malicious nodes to mimic legitimate nodes encountering slow connectivity, a problem intensified in very stochastic traffic environments where higher node latencies create even stealthier Slow DoS conditions.</div><div>The contribution this paper presents is a flexible <em>single attribute intrusion detection system</em> (SA-IDS) for IoT networks, which employs a novel variable threshold range for just the delta time network attribute, to accurately detect Slow DoS attacks in highly stochastic traffic, while crucially still being able to reliably discriminate malicious from legitimate slow node activity. Experimental results in a live IoT network compellingly demonstrate the superior detection performance of SA-IDS under the stealthiest Slow DoS attack conditions, where genuine nodes with high latency are almost indistinguishable from malicious nodes, thus rendering existing Slow DoS detection methods ineffective that rely solely on static thresholds based on network traffic attribute analysis.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"30 ","pages":"Article 101512"},"PeriodicalIF":6.0,"publicationDate":"2025-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143377136","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}
{"title":"An IoT-enabled omnidirectional mobile system for home-based rehabilitation of upper and lower limbs","authors":"Lian-Wang Lee , Shih-Ting Wang , I-Hsum Li","doi":"10.1016/j.iot.2025.101525","DOIUrl":"10.1016/j.iot.2025.101525","url":null,"abstract":"<div><div>Robotic systems have made significant strides in stroke rehabilitation, evolving from prototypes to clinical applications. However, challenges remain, including limited clinic accessibility, high costs, bulky equipment, and a lack of versatility for upper and lower limb therapy. Integration into home environments also poses difficulties. To address these issues, we introduce OmniRehab, an innovative home-based rehabilitation system tailored for stroke patients with hemiplegia. OmniRehab combines upper and lower limb rehabilitation on a single omnidirectional platform, supporting both passive and active training modes to accommodate different recovery stages. In passive mode, it provides guided assistance, while in active mode, it promotes voluntary muscle control and neuromuscular re-education. The system leverages Internet of Things (IoT) technology for real-time remote supervision, enabling clinicians to monitor progress and adjust training programs dynamically. To enhance engagement, OmniRehab includes virtual rehabilitation games, offering immersive training that motivates patients while helping them master complex tasks. Experimental validation confirms its effectiveness, demonstrating OmniRehab as a cost-efficient, versatile solution for home-based stroke rehabilitation.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"30 ","pages":"Article 101525"},"PeriodicalIF":6.0,"publicationDate":"2025-02-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143348010","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}
Marcos Lupión, Vicente González-Ruiz, Juan F. Sanjuan, Pilar M. Ortigosa
{"title":"Privacy-aware fall detection and alert management in smart environments using multimodal devices","authors":"Marcos Lupión, Vicente González-Ruiz, Juan F. Sanjuan, Pilar M. Ortigosa","doi":"10.1016/j.iot.2025.101526","DOIUrl":"10.1016/j.iot.2025.101526","url":null,"abstract":"<div><div>Falls are a leading cause of injury and mortality, especially among the elderly. While camera-based fall detection systems have shown success, they raise significant privacy concerns. Alternatives using wearable sensors or thermal cameras offer comparable accuracy but have yet to be combined for accurate fall detection. Additionally, most research focuses on fall detection without addressing post-fall user’s condition or personalized alerts. This study aims to develop a privacy-aware fall detection system leveraging wearable sensors and thermal cameras. In addition, an alert system integrates devices such as voice assistants and speakers to assess the user’s status after the fall and notify the event. The system improves detection accuracy, addresses privacy concerns, and enhances alert management through personalized responses. We propose an Internet of Things (IoT)-based system integrating all sensors and devices previously mentioned. Edge-based computation enables real-time detection, with Internet connectivity used only for sending alerts in case of a fall. Various machine learning algorithms and sensor sources are evaluated to determine their impact on detection accuracy. Experimental results show that fall detection using a convolutional neural network with thermal images from three viewpoints achieves an F1-score above 0.98. Similarly, traditional machine learning algorithms applied to wearable sensor data showed high performance (0.93 F1-score). Post-processing techniques effectively remove false positives, improving reliability and adoption in real environments. The proposed system ensures high accuracy while addressing privacy concerns. By integrating multimodal devices and edge-based computing, it offers a scalable, real-time solution for smart environments, ensuring timely responses through personalized alerts after falls.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"30 ","pages":"Article 101526"},"PeriodicalIF":6.0,"publicationDate":"2025-02-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143222785","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}
{"title":"PD-DRL: Towards privacy-preserving and energy-sustainable UAV crowdsensing","authors":"Xiaohui Chen , Kaimin Wei , Jinpeng Chen , Yongdong Wu","doi":"10.1016/j.iot.2025.101520","DOIUrl":"10.1016/j.iot.2025.101520","url":null,"abstract":"<div><div>Due to the high altitude advantage of unmanned aerial vehicles (UAVs), UAV crowdsensing has been extensively utilized in smart cities and harsh environments. However, UAVs have limited operational duration owing to energy constraints, dramatically diminishing their working efficiency. Moreover, their flight data is recorded and transmitted in unencrypted text, making it vulnerable to privacy breaches. We propose a privacy-preserving dual-model deep reinforcement learning approach (PD-DRL) to end it. It not only adaptively employs contextual knowledge to switch flight modes to enhance UAVs’ working efficiency but also safeguards the confidentiality of sensitive information during model training. PD-DRL consists of privacy-preserving deep reinforcement learning (P-DRL) and dual-model deep reinforcement learning (D-DRL). The former may integrate two distinct policies to switch between data collection and charging modes adaptively, hence optimizing the UAVs’ flight route. The latter can produce synthetic data to replace raw data during model training, thereby protecting the privacy of sensitive information. Ultimately, we conduct security discussions and comprehensive experiments to assess the effectiveness of PD-DRL. The discussion and experimental results demonstrate that PD-DRL surpasses other comparative algorithms, confirming its efficacy and safety.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"30 ","pages":"Article 101520"},"PeriodicalIF":6.0,"publicationDate":"2025-02-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143348285","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}
{"title":"A Fuzzy-based System for assessment of relational trust in IoT and social networks","authors":"Shunya Higashi , Phudit Ampririt , Ermioni Qafzezi , Makoto Ikeda , Keita Matsuo , Leonard Barolli","doi":"10.1016/j.iot.2025.101528","DOIUrl":"10.1016/j.iot.2025.101528","url":null,"abstract":"<div><div>In modern digital ecosystems, trust plays a critical role in ensuring secure and reliable interactions across various entities, including humans and machines. As technologies such as 5G wireless networks and the Internet of Things (IoT) drive unprecedented complexity in these environments, the demand for flexible and effective trust evaluation systems has grown exponentially. This paper presents a Fuzzy-based System for Assessment of Relational Trust (FSART), which utilizes fuzzy logic to evaluate trust levels between entities. We implemented two models (FSARTM1 and FSARTM2) considering three parameters: Influence (If), Importance (Ip), and Similarity (Sm) for FSARTM1, while for FSARTM2 we considered Reputation (Rp) as an additional parameter. The simulation results indicate that increasing the values of these parameters leads to a corresponding increase in Relational Trust (RT). For FSARTM1, when Ip is 0.9, all RT values exceed 0.5, while in FSARTM2 when If is 0.9 and moderate values of other parameters, RT consistently remains above 0.5. These results suggest that FSARTM2 provides a more accurate assessment by incorporating Rp, making it a more robust tool for trust evaluation in complex digital ecosystems, including social media, collaborative environments, and IoT systems.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"30 ","pages":"Article 101528"},"PeriodicalIF":6.0,"publicationDate":"2025-02-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143348284","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}
Muhammad Ali , Yasir Saleem , Sadaf Hina , Ghalib A. Shah
{"title":"DDoSViT: IoT DDoS attack detection for fortifying firmware Over-The-Air (OTA) updates using vision transformer","authors":"Muhammad Ali , Yasir Saleem , Sadaf Hina , Ghalib A. Shah","doi":"10.1016/j.iot.2025.101527","DOIUrl":"10.1016/j.iot.2025.101527","url":null,"abstract":"<div><div>The widespread adoption of Internet of Things (IoT) devices has introduced numerous vulnerabilities, particularly in firmware over-the-air (OTA) updates. These updates are essential for improving device functionality and addressing security vulnerabilities. However, they have increasingly become the focus of distributed denial of service (DDoS) attacks designed to disrupt the update process. Historically, the infamous Mirai botnet and its variants have exploited IoT vulnerabilities to carry out successful DDoS attacks. In recent years, deep learning models, especially Vision Transformers, have gained significant attention due to their exceptional performance in image classification tasks. To optimize detection and alert mechanisms, this novel study proposes a DDoSViT framework. This Vision Transformer (ViT)-based multi-vector DDoS and DoS attack detection framework converts attack flows into images and trains Vision Transformers on an attack image dataset. To validate the proposed framework, this study extensively reviewed diverse datasets and selected CICIoT2023 and CICIoMT2024 datasets ensuring these contain real-world attack scenarios and multi-vector real attacks. The proposed methodology and rigorous experimentation demonstrated 99.50% accuracy in multi-class classification across 23 different variants of DDoS and DoS attacks, outperforming contemporary models. The model’s performance was assessed using metrics such as accuracy, precision, recall, and F1-score. This research provides significant benefits to security practitioners and administrators, offering reduced false positives and reliable alerts during firmware over-the-air updates in IoT-edge devices.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"30 ","pages":"Article 101527"},"PeriodicalIF":6.0,"publicationDate":"2025-02-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143377135","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}
Amara Riaz , Waseem Iqbal , Faiz Ul Islam , Madiha Hassan , Rabiya Tariq , Abdellah Chehri , Ahmad Fayyaz Madni
{"title":"S2H-securing smart homes: A blockchain-based preservation approach","authors":"Amara Riaz , Waseem Iqbal , Faiz Ul Islam , Madiha Hassan , Rabiya Tariq , Abdellah Chehri , Ahmad Fayyaz Madni","doi":"10.1016/j.iot.2025.101523","DOIUrl":"10.1016/j.iot.2025.101523","url":null,"abstract":"<div><div>Smart home systems are becoming more prevalent and popular in modern society, as they can provide convenience, comfort, and efficiency to the users. The proliferation of the Internet of Things (IoT) creates a network of interconnected devices generating vast amounts of data in real-world applications like smart cities, connected appliances, and supply chain management. This growth necessitates addressing challenges related to data security, integrity, and regulatory frameworks for emerging applications and integrations. However, traditional smart home systems are susceptible to intrusion and hacking. Transmission between devices and central systems can be intercepted or personal data can be misused. Since these systems rely on cloud services or central servers, they face risk of centralized data breaches, single points of failure, and control. Smart home systems also face other issues with include scalability, privacy, interoperability, and security. Furthermore, the users have limited control over their devices and data. Blockchain technology offers a potential solution for securing and preserving user and data integrity in a decentralized manner. Hyperledger Fabric, a permissioned blockchain platform, stands out for its open-source nature, modular architecture, and high performance, making it a versatile tool for addressing these concerns within the smart home IoT domain. In this research paper, a blockchain-enabled architecture based on Hyperledger Fabric is presented to address the data security and integrity challenges associated with the smart home IoT. A new architecture is introduced to enable this integration, and is developed and deployed, and its performance is analyzed in various scenarios. The evaluation results demonstrate that the proposed solutions outperform the existing solutions and is feasible and effective over the existing solutions.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"30 ","pages":"Article 101523"},"PeriodicalIF":6.0,"publicationDate":"2025-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143349495","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}
Tianshuai Zheng , Ye Du , Kaisheng Hua , Xuesong Wu , Shaosui Yuan , Xiaolong Wang , Qifang Chen , Jinglei Tan
{"title":"Predictive analytics for cyber-attack timing in power Internet of Things: A FlipIt game-theoretic approach","authors":"Tianshuai Zheng , Ye Du , Kaisheng Hua , Xuesong Wu , Shaosui Yuan , Xiaolong Wang , Qifang Chen , Jinglei Tan","doi":"10.1016/j.iot.2025.101522","DOIUrl":"10.1016/j.iot.2025.101522","url":null,"abstract":"<div><div>The Power Internet of Things is increasingly challenged by complex security threats, which highlights the importance of developing predictive models for attack behaviors and implementing targeted defensive measures. In response to the challenges of traditional network attack predictors, which fail to forecast attack times, and the lack of integration of attack–defense confrontation processes in these methods, this paper proposes a novel method based on FlipIt games. This method not only aims to predict the timing of attacks but also considers the dynamic nature of attack–defense confrontations, adaptively suggesting defense strategies. The paper constructs a strategy evolution probability model for both attackers and defenders based on the infectious disease model and analyzes the interactive process of confrontation between them. It then establishes a network attack time prediction model based on FlipIt games and proposes an attack time strategy prediction algorithm that incorporates exponential probability distribution into the revenue calculation process to predict the timing of network attacks. Finally, by setting up simulation environments and conducting simulations using MATLAB, the proposed model is verified to effectively analyze the attack time of the virus and provide corresponding defense strategies in real-time. In the process of attack and defense, to achieve optimal attack benefits, attackers should prioritize selecting low-frequency and low-cost attack strategies.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"30 ","pages":"Article 101522"},"PeriodicalIF":6.0,"publicationDate":"2025-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143348283","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}
{"title":"IoT-based obstacle avoidance and navigation for UGVs in wooded environments using adaptive fuzzy artificial potential field","authors":"Cheng-Jian Lin , Bing-Hong Chen , Jyun-Yu Jhang","doi":"10.1016/j.iot.2025.101524","DOIUrl":"10.1016/j.iot.2025.101524","url":null,"abstract":"<div><div>Internet of Things (IoT) applications are increasingly popular, but data collection can be challenging. Unmanned ground vehicles (UGVs) are a practical solution, but navigation control remains difficult. In this study, we develop a framework based on IoT and adaptive fuzzy artificial potential field (AFAPF) for obstacle avoidance and navigation applications in wooded environments. A UGV was deployed in a wooded area with dense obstacles, and light detection and ranging (LiDAR) was used to scan its environment. The proposed IoT-based UGV framework comprises an integrated monitoring platform, an NVIDIA Jetson AGX Xavier, a global positioning system, LiDAR, the AFAPF algorithm, a battery, and a UGV control system; together, these ensure the stable movement of the UGV in unknown environments. In the proposed AFAPF obstacle avoidance method, the distance between the UGV and an obstacle and the density of the LiDAR point cloud representing an obstacle are input to an adaptive fuzzy decision-making method, which adjusts the expansion radius of each obstacle. This enables the UGV to immediately and effectively avoid obstacles. In experiments conducted in two wooded environments unknown by the UGV, the proposed AFAPF method reduced navigation time and driving distance by an average of 17.62 % and 14.87 %, respectively, compared with a comparable nonfuzzy method.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"30 ","pages":"Article 101524"},"PeriodicalIF":6.0,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143222784","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}
{"title":"TinyResViT: A lightweight hybrid deep learning model for on-device corn leaf disease detection","authors":"Van-Linh Truong-Dang, Huy-Tan Thai, Kim-Hung Le","doi":"10.1016/j.iot.2025.101495","DOIUrl":"10.1016/j.iot.2025.101495","url":null,"abstract":"<div><div>The increasing prevalence of corn leaf diseases poses a significant threat to global food security, necessitating efficient and accurate detection methods. To address this challenge, we introduce TinyResViT, a lightweight yet efficient hybrid deep learning model designed by combining Residual Network (ResNet) and Vision Transformer (ViT) for leaf disease detection. This combination leverages the strengths of ResNet in extracting local features and ViT in capturing global interactions among features. In addition, a novel downsampling block connecting ResNet and ViT is proposed to eliminate redundant model weights. The evaluation results on the PlantVillage and Bangladeshi Crops Disease datasets show TinyResViT’s superior performance, achieving F1-scores of 97.92% and 99.11%, respectively. The model also maintains a high processing speed of 83.19 Frames Per Second (FPS) and a low computational cost of 1.59 Giga Floating Point Operations (GFLOPs), outperforming existing deep neural networks and state-of-the-art approaches.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"30 ","pages":"Article 101495"},"PeriodicalIF":6.0,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143222781","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}