IoT Ecosystem Research Articles

The Impact of 5G on IoT Ecosystems

The convergence of 5G and IoT is revolutionizing industries by enhancing connectivity, scalability, and security. This synergy enables efficient edge computing, reducing latency and optimizing data processing. Security measures like authentication and encryption are crucial for protecting sensitive data. The integration of 5G and IoT opens innovative business avenues, transforming manufacturing, logistics, healthcare, and more. Businesses can optimize operations, automate processes, and enhance customer experiences, making it essential to embrace this transformative potential for staying competitive and capitalizing on advancements.

A low-cost centralized IoT ecosystem for enhancing oyster mushroom cultivation

The consumption of mushrooms has skyrocketed in recent years worldwide. The majority of farmers in developing countries still rely on the traditional approach to mushroom cultivation. So, modern technology needs to be adopted to enhance productivity to meet local demand. In addition, farmers face complex supply chain problems, a lack of direct communication with agronomists, and frequent outbreaks of diseases. This paper presents a low-cost centralized IoT ecosystem for addressing the aforementioned issues. The ecosystem provides real-time monitoring and automation of mushroom farmhouses, agro-eCommerce for convenient trade, agronomist advisory support, and disease detection with recommendations for early disease diagnosis and remedy. A small farmhouse with two rooms was built to validate the system's performance. The favorable climatic condition was maintained for oyster mushroom cultivation in the controlled room, whereas the traditional method was followed in the ordinary room. The mushroom was cultivated for three consecutive seasons throughout the year in both rooms. We found that the total production in the controlled room exceeded the yield in the ordinary room by around 49%, provided the same batch of seeds was used in both cases. The disease detection model achieved an accuracy of 98.33%, where farmers can upload the suspected image to the IoT ecosystem and get the predicted disease with relevant suggestions. By utilizing this IoT ecosystem can assist farmers in maintaining the required climatic conditions, streamline the problem of intermediaries while facilitating information exchange with agronomists, and aid in early disease detection and remedy recommendations.

Multi-Layer Digital Services Increase Developers’ Requirements to Agriculture IoT Platforms

Highlights Digital ecosystems in agriculture enable a new class of digital services that span over several layers of the IoT stack. This work defines digital ecosystems in agriculture based on IoT layers and utilized technologies. An example for a multi-layer digital service is developed, deployed, and tested using the NEVONEX Ecosystem. Surveys reveal software providers require more platform functionalities and early iteration testing on real farms. Abstract. In recent years, digital platforms in agriculture went through a phase of acquisitions and consolidation, where big players like agrochemical companies (Agrichems) and agricultural equipment manufacturers (OEMs) worked on expanding their technology stacks to build strategic portfolios of digital service offerings. To operate farm equipment efficiently, a combination of platforms and technologies is often needed, leading to the emergence of digital Agri-ecosystems. With the rising implementation of IoT technology, digital Agri-ecosystems enable multi-layer digital services and break down established categories (cloud-based and embedded). Content providers and developers creating those digital services face three options: aggregated cloud APIs (application programming interfaces), engineering service providers with proprietary technology stacks, and dedicated IoT ecosystems offering agnostic end-to-end workflows for development and deployment (first known example: NEVONEX). It is not yet fully understood how using an end-to-end IoT ecosystem changes developer requirements in comparison to existing solutions. Therefore, in this study, an example of a multi-layer digital service is developed and tested. Expert interviews (n = 21) explore relevant developer experiences and requirements. A consecutive survey (n = 30; NEVONEX developer conference) validates the findings. Results show that IoT- ecosystems speed up development and deployment cycles, save resources, and improve interoperability in operations. Engineering service providers remain very important players. Partner management, communication, abstraction of interfaces, testing infrastructure, and early end-user input are required by developers. In conclusion, IoT- ecosystems are beneficial for multi-layer digital service development; however, to fully satisfy developers and content providers, adjustments to platform functionalities and better testing opportunities on real farms are needed. Keywords: Automation, Digital Ecosystem, Farm equipment, NEVONEX

Innovative IoT security protocol: High-accuracy device identification and resilience against credential compromise (HADIRACC)

The IoT ecosystem faces increasingly complex security challenges due to the rapid growth of global IoT devices. Security risks related to device identification and credential compromise are on the rise, especially with the proliferation of IoT devices in various aspects of life. This research highlights the need to address these vulnerabilities through the development of robust security protocols, aiming to create a more secure IoT ecosystem and enhance user trust in this technology. The objective of the research is the development of an innovative IoT security protocol; High-Accuracy Device Identification and Resilience Against Credential Compromise (HADIRACC). This paper contributes significantly to enhancing the security and reliability of the IoT ecosystem. The research methods employed encompass the development of security protocols, the development of a proximity-based solution, and the classification of IoT devices using data processing techniques and machine learning-based classification. This study involves the collection and pre-processing of datasets, training different classifiers using 70% of the dataset, and testing the classifiers using the remaining 30%. The proposed protocol can effectively enhance the security of IoT devices by addressing various scenario-based attacks. Furthermore, the results of the analysis of the five classifiers used in this study indicate that Random Forest has the highest F1 score accuracy, reaching 88.8%. This suggests that Random Forest, as a classifier, can make the most accurate predictions compared to other classifiers.

An analytical approach to network with IoT security using NodeMCU access point-prevention technique

This paper focuses on a very pertinent issue in the field of cybersecurity, particularly concerning the increased use of public Wi-Fi and the proliferation of IoT devices. The scenario, where an attacker captures user details through a malicious access point set up through a NodeMCU, is a practical illustration of a Man-in-the-Middle (MitM) attack. These attacks are especially concerning in the context of smart homes and smart cities, where security breaches can lead to severe privacy invasions and disruptions of essential services. The NodeMCU, being a low-cost, open-source IoT platform, is accessible for creating such malicious access points. It can be programmed to mimic legitimate Wi-Fi hotspots to intercept the data of unsuspecting users. This type of attack can enable unauthorized access to sensitive information such as login credentials, personal data, and even control over connected IoT devices. This approach is user-friendly and can significantly reduce the risk of users unknowingly connecting to malicious websites. The contribution of this paper includes a demonstration and analysis of a common network and IoT attack and a novel method for detecting fraudulent URLs, particularly those used in phishing attacks. By addressing these aspects, the paper makes a significant contribution to the field of cybersecurity and helps foster a more secure and resilient network and IoT ecosystem.

DAIS: deep artificial immune system for intrusion detection in IoT ecosystems

DAIS: deep artificial immune system for intrusion detection in IoT ecosystems

Ensuring Security and Privacy in loT Ecosystems: A Comprehensive Approach

The Internet of Things (IoT) ecosystem introduces significant security and privacy challenges, including public perception, eavesdropping, unwanted public profiles, and vulnerability to hacking. The expanding significance of the IoT in our daily lives raises several security and privacy concerns, such as side-channel attacks, illegal chats, and link-ability. Such problems could jeopardize the IoT if they are not addressed. These are derived from two main reasons. One is that IoT gadgets' restricted processing, memory, and bandwidth capabilities must be improved by directly applying conventional Internet security approaches. Another reason is the need for acknowledged IoT security and privacy standards and the methods necessary to implement them. This research paper aims to propose a comprehensive approach to addressing these challenges. It explores the various security measures and tools, such as network visibility, segmentation, API security, continuous software updates, DNS filtering, education and training, encryption, and multi-factor authentication. This work also emphasizes the importance of user education and awareness in understanding the inherent risks associated with IoT systems. Furthermore, it discusses the need for standardization, compliance, and establishing a secure path for collaboration between social networks and privacy concerns in the IOT ecosystem.

Security Implications of IoT-Enabled Mobile Net Facial Recognition System

Face recognition technology is gaining popularity for security, access management, and user identification. A novel facial recognition method employing cutting-edge deep learning algorithms and attention processes reduces false positives in this study. This technique was designed to approach facial recognition differently. We demonstrate statistically substantial recognition gains over current approaches through extensive research and experimentation. The recommended solution uses an attention device and a complex feature extraction module. The pieces work together to highlight distinctive characteristics and facial identifiers. To optimize performance and generalization across datasets, data addition and hyper parameter adjustment are used to fine-tune the model. We do this for maximum benefit. Studies on the issue may help us understand the multiple reasons that make ablation so successful. We also discuss facial recognition technology's moral difficulties, including fairness and user privacy. We also emphasize cautious distribution. Our findings expand facial recognition technology knowledge and pave the way for future studies. This study demonstrates that better Mobile Net models and Internet of Things technologies increase the accuracy of mobile facial recognition. The project overcomes the challenge of providing powerful AI tools in resource-constrained situations by utilizing IoT infrastructures and effective, lightweight Mobile Net architectures. Extensive testing demonstrates that the technique increases identification rates and outperforms existing models, showing its suitability for real-time operations. The Internet of Things enables data mobility and cross-device model usage. This illustrates that the IoT ecosystem can enable effective and scalable security solutions.

Ontology-based Neurointerface IoT Integration Approach

Recently, there is a surge of interest in employing neurocomputer interfaces for a control contours implementation, especially for different infrastructures of Internet of Things. However, due to a low-level nature of such devices and related software tools, neurointerface integration with a large variety of IoT devices is quite a tedious task, and the one that requires a lot of knowledge in the neuroscience and signal processing to boot. In the paper, we propose an ontology-driven solution for facing the upcoming challenges of unified integration of brain-computer interfaces into IoT ecosystems. We demonstrate an adaptable mechanism for integrating brain-computer interfaces into the Internet of Things infrastructure by introducing an intermediate layer – a smart mediator that will be responsible for communication between the environment and the neurointerface. The mediator’s software is generated automatically, and this process is driven by a managing ontology. The proposed formal model and the system's implementation are described. The approach we have developed enables researchers and engineers without strong background in brain–computer interface to automate the integration neurointerfaces with different infrastructures of Internet of Things.

AI-Powered Integrated With Encoding Mechanism Enhancing Privacy, Security, and Performance for IoT Ecosystem

AI-Powered Integrated With Encoding Mechanism Enhancing Privacy, Security, and Performance for IoT Ecosystem

One Bad Apple Spoils the Barrel: Understanding the Security Risks Introduced by Third-Party Components in IoT Firmware

Currently, the development of IoT firmware heavily depends on third-party components (TPCs) to improve development efficiency. Nevertheless, TPCs are not secure, and the vulnerabilities in TPCs will influence the security of IoT firmware. Existing works pay less attention to the vulnerabilities caused by TPCs, and we still lack a comprehensive understanding of the security impact of TPC vulnerability against firmware. To fill in the knowledge gap, we design and implement <sc xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">FirmSec</small> , which leverages syntactical features and control-flow graph features to detect the TPCs in firmware, and then recognizes the corresponding vulnerabilities. Based on <sc xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">FirmSec</small> , we present the first large-scale analysis of the security risks raised by TPCs on 34,136 firmware images. We successfully detect 584 TPCs and identify 128,757 vulnerabilities caused by 429 CVEs. Our in-depth analysis reveals the diversity of security risks in firmware and discovers some well-known vulnerabilities are still rooted in firmware. Besides, we explore the geographical distribution of vulnerable devices and confirm that the security situation of devices in different regions varies. Our analysis also indicates that vulnerabilities caused by TPCs in firmware keep growing with the boom of the IoT ecosystem. Further analysis shows 2,478 commercial firmware images have potentially violated GPL/AGPL licensing terms.

Intrusion Detection in IoT Networks Using Machine Learning Techniques

The advent of the IoT has undeniably transformed the manner in which we connect with the world innovative solutions across a multitude of sectors. However, the proliferation of IoT applications has brought to the fore a complex and multifaceted problem that warrants immediate attention: the security and energy efficiency challenges within IoT networks. As the number of IoT devices continues to surge and their applications diversify, the demand for ubiquitous and secure data access has never been greater. These applications, ranging from healthcare monitoring to industrial automation, require not only real-time data processing but also the assurance of data security and privacy. So, the research explores the machine learning techniques application for intrusion detection in IoT networks, aiming to enhance security in the rapidly evolving landscape of interconnected devices. The research emphasizes the significance of proactive measures in safeguarding IoT ecosystems and highlights the potential of machine learning to detect and mitigate intrusions effectively. In this research, a model was developed for detecting anomalies in Internet of Things networks using artificial neural networks. The research aims to develop and evaluate an effective intrusion detection model for IoT networks by leveraging machine learning techniques. The purpose is to enhance the security posture of interconnected devices, addressing the unique challenges posed by the dynamic and heterogeneous nature of IoT environments. The study tries to contribute important experiences and functional answers to reinforce the strength of IoT networks against developing digital dangers.

Malware Detection in IoT Systems using Machine Learning Techniques

Malware detection in IoT environments necessitates robust methodologies. This study introduces a CNN-LSTM hybrid model for IoT malware identification and evaluates its performance against established methods. Leveraging K-fold cross-validation, the proposed approach achieved 95.5% accuracy, surpassing existing methods. The CNN algorithm enabled superior learning model construction, and the LSTM classifier exhibited heightened accuracy in classification. Comparative analysis against prevalent techniques demonstrated the efficacy of the proposed model, highlighting its potential for enhancing IoT security. The study advocates for future exploration of SVMs as alternatives, emphasizes the need for distributed detection strategies, and underscores the importance of predictive analyses for a more powerful IOT security. This research serves as a platform for developing more resilient security measures in IoT ecosystems.

Relativistic Digital Twin: Bringing the IoT to the future

Complex IoT ecosystems often require the usage of Digital Twins (DTs) of their physical assets in order to perform predictive analytics and simulate what-if scenarios. DTs are able to replicate IoT devices and adapt over time to their behavioral changes. However, DTs in IoT are typically tailored to a specific use case, without the possibility to seamlessly adapt to different scenarios. Further, the fragmentation of IoT poses additional challenges on how to deploy DTs in heterogeneous scenarios characterized by the usage of multiple data formats and IoT network protocols. In this paper, we propose the Relativistic Digital Twin (RDT) framework, through which we automatically generate general-purpose DTs of IoT entities and tune their behavioral models over time by constantly observing their real counterparts. The framework relies on the object representation via the Web of Things (WoT), to offer a standardized interface to each of the IoT devices as well as to their DTs. To this purpose, we extended the W3C WoT standard in order to encompass the concept of behavioral model and define it in the Thing Description (TD) through a new vocabulary. Finally, we evaluated the RDT framework over two disjoint use cases to assess its correctness and learning performance, i.e., the DT of a simulated smart home scenario with the capability of forecasting the indoor temperature, and the DT of a real-world drone with the capability of forecasting its trajectory in an outdoor scenario. Experiments show that the generated DT can estimate the behavior of its real counterpart after an observation stage, regardless of the considered scenario.

An IoT Ecosystem Platform for the Evaluation of Blockchain Feasibility

An IoT Ecosystem Platform for the Evaluation of Blockchain Feasibility

Malware Cyber Threat Intelligence System for Internet of Things (IoT) Using Machine Learning

Cyber Intelligence (CI) is a sophisticated security solution that uses machine learning models to protect networks against cyber-attack. Security concerns to IoT devices are exacerbated because of their inherent weaknesses in memory systems, physical and online interfaces, and network services. IoT devices are vulnerable to attacks because of the communication channels. That raises the risk of spoofing and Denial-of-Service (DoS) attacks on the entire system, which is a severe problem. Since the IoT ecosystem does not have encryption and access restrictions, cloud-based communications and data storage have become increasingly popular. An IoT-based Cyber Threat Intelligence System (IoT-CTIS) is designed in this article to detect malware and security threads using a machine learning algorithm. Because hackers are continuously attempting to get their hands on sensitive information, it is important that IoT devices have strong authentication measures in place. Multifactor authentication, digital certificates, and biometrics are just some of the methods that may be used to verify the identity of an Internet of Things device. All devices use Machine Learning (ML) assisted Logistic Regression (LR) techniques to address memory and Internet interface vulnerabilities. System integrity concerns, such as spoofing and Denial of Service (DoS) attacks, must be minimized using the Random Forest (RF) Algorithm. Default passwords are often provided with IoT devices, and many users don’t bother to change them, making it simple for cybercriminals to get access. In other instances, people design insecure passwords that are easy to crack. The results of the experiments show that the method outperforms other similar strategies in terms of identification and wrong alarms. Checking your alarm system’s functionality both locally and in terms of its connection to the monitoring centre is why you do it. Make sure your alarm system is working properly by checking it on a regular basis. It is recommended that you do system tests at least once every three months. The experimental analysis of IoT-CTIS outperforms the method in terms of accuracy (90%), precision (90%), F-measure (88%), Re-call (90%), RMSE (15%), MSE (5%), TPR (89%), TNR (8%), FRP (89%), FNR (8%), Security (93%), MCC (92%).

A comparative analysis of using ensemble trees for botnet detection and classification in IoT

Enhancing IoT security is a corner stone for building trust in its technology and driving its growth. Limited resources and diversified nature of IoT devices make them vulnerable to attacks. Botnet attacks compromise the IoT systems and can pose significant security challenges. Numerous investigations have utilized machine learning and deep learning techniques to identify botnet attacks in IoT. However, achieving high detection accuracy with reasonable computational requirements is still a challenging research considering the particularity of IoT. This paper aims to analytically study the performance of the tree based machine learning in detecting botnet attacks for IoT ecosystems. Through an empirical study performed on a public botnet dataset of IoT environment, basic decision tree algorithm in addition to ensemble learning of different bagging and boosting algorithms are compared. The comparison covers two perspectives: IoT botnet detection capability and computational performance. Results demonstrated that the significant potential for the tree based ML algorithms in detecting network intrusions in IoT environments. The RF algorithm achieved the best performance for multi-class classification with accuracy rate of 0.999991. It achieved also the highest results in all other measures.

Design of Security Chips in the IoT Ecosystem

With the rapid growth of IoT devices, security issues are becoming increasingly prominent. The main research object of this article is the Internet of Things security chip. In response to the difficulties faced by the current Internet of Things security and the importance of Internet of Things security, this article mainly introduces the basic design principles of Internet of Things security chips, and provides a detailed introduction to the structures and applications of three classic models: TEE, HSM, and TPM. In addition, comparative analysis was conducted on these models. IoT security is a highly challenging field that requires comprehensive consideration of security issues at different levels and stages. The IoT security chips play a crucial role in ensuring the security and data privacy of IoT devices. In the future, IoT security chips may be combined with emerging technologies such as blockchain, artificial intelligence, and quantum encryption to enhance security and credibility.

A cost-effective LoRaWAN-based IoT localization method using fixed reference nodes and dual-slope path-loss modeling

Recently, RSSI-based localization has gained popularity for outdoor localization within the IoT ecosystem due to its cost-effectiveness, low-power and low-cost deployment, and ability to operate loT nodes for years on a single battery. However, this approach typically sacrifices accuracy, resulting in location estimates in the tens or hundreds of meters. For example, LoRaWAN communications have been widely used in IoT applications, being an attractive solution due to their long-range coverage, low implementation cost, and higher autonomy. However, RSSI-based LoRaWAN location methods suffer from multipath and fading interference which results in the near-far problem, impacting ranging accuracy for short and long distances, and thus leading to an overall decrease in the localization accuracy. In this article, we address the low accuracy of RSSI based localization challenge for outdoor IoT node localization by computing the Path Loss (PL) parameters of LoRaWAN, for short and long distances separately, thus providing a dual-slope PL model. In addition, some IoT nodes in specific locations are adopted as Reference Nodes (RNs), whose main task is to estimate the interference effect on the transmitted signals dynamically. The proposed model has been evaluated using a publicly available LoRaWAN dataset collected in urban areas in the city of Antwerp, Belgium, which serves as a benchmark for the evaluation of the results. Its effectiveness is assessed by simulation and comparison to the state-of-the-art. In addition, results are compared with the derived Cramer–Rao Lower Bound (CRLB). The localization error achieves a median error of 117 m and a mean error of 236 m.

Learning autoencoder ensembles for detecting malware hidden communications in IoT ecosystems

Modern IoT ecosystems are the preferred target of threat actors wanting to incorporate resource-constrained devices within a botnet or leak sensitive information. A major research effort is then devoted to create countermeasures for mitigating attacks, for instance, hardware-level verification mechanisms or effective network intrusion detection frameworks. Unfortunately, advanced malware is often endowed with the ability of cloaking communications within network traffic, e.g., to orchestrate compromised IoT nodes or exfiltrate data without being noticed. Therefore, this paper showcases how different autoencoder-based architectures can spot the presence of malicious communications hidden in conversations, especially in the TTL of IPv4 traffic. To conduct tests, this work considers IoT traffic traces gathered in a real setting and the presence of an attacker deploying two hiding schemes (i.e., naive and “elusive” approaches). Collected results showcase the effectiveness of our method as well as the feasibility of deploying autoencoders in production-quality IoT settings.