Machine learning-driven Security Frameworks for IoT in Next-Generation Wireless Networks

<span lang="EN-US">With the proliferation of internet of things (IoT) devices, ensuring the security of these interconnected systems has become a critical concern. Cyberattacks targeting IoT devices pose significant threats to individuals and organizations due to the generation of vast amounts of data across many connected devices, which traditional centralized methods cannot solve. Federated learning (FL) could be a promising solution to mitigate privacy concerns associated with centralized approaches and address cybersecurity concerns. This paper uses FL and deep learning (DL) approaches to cybersecurity in IoT applications. The goal of cyber security is achieved by forming a federation of acquired and shared models at the head of the various participants. We use inception time and multi-head attention (CNN) algorithm based on FL to detect cyber-attacks and avoid data privacy leaks under two distribution modes, namely IID and Non-IID. In contrast, the FedAvg and FedMA algorithms aggregate local model updates. A global model is produced after several communication rounds between the IoT devices and the model parameter server. Cyber threats are simulated using edge-IIoT datasets. Experiment results show that the federated inception model's best global accuracy was 93, 91%, and 93, 49% using multi-head attention.</span>

Internet of Things (IoT) have opened the door to a world of unlimited possibilities for implementations in varied sectors in society, but it also has many challenges. One of those challenges is security and privacy. IoT devices are more susceptible to security threats and attacks. Due to constraints of the IoT devices such as area, power, memory, etc., there is a lack of security solutions that are compatible with IoT devices and applications, which is leading this world of securely connected things to the “internet of insecure things.” A promising solution to this problem is going beyond the standard or classical techniques to implementing the security solutions in the hardware of the IoT device. The integration of emerging technologies in IoT networks, such as machine learning, blockchain, fog/edge/cloud computing, and quantum computing have added more vulnerable points in the network. This paper introduces a comprehensive study on IoT security threats and solutions. Additionally, this survey outlines how emerging technologies such as machine learning and blockchain are integrated in IoT, challenges resulted from this integration, and potential solutions to these challenges. The paper utilizes the 4-layer IoT architecture as a reference to identify security issues with corresponding solutions.

The interconnected system consisting of tangible items featuring the capacity to transmit information is called the Internet of Things (IoT). The design encompasses various gadgets, including industrial machinery and electrical appliances. IoT devices are unprotected from safety hazards; eventually, it is important to remain vigilant about this provision to preserve data and establish that IoT systems can withstand new hacking attempts. The research seeks to provide a novel approach for machine learning (ML)--based danger indicator identification in IoT environments. Thus, a Binary Chimpanzee-Optimized Fine-Tuned Linear Least Squares Twin Support Vector Machine (BC-FTLLS-TSVM) method is introduced for detecting attack signs in IoT settings. To improve the efficiency of the proposed threat identification mechanism, an N-BaIoT dataset that accommodates the unpredictability of damaging attacks against IoT gadgets is utilized. The method includes the BCOA to feed the selection of features and greater parameters using the FTLLS-TSVM, to advance the accuracy of monitoring IoT threat signs. The proposed framework is performed by applying Python programming. Various metrics, such as Accuracy (97.50%), Precision (97.85%), F1 Score (98.35%), and False Positive Rate (FPR) (2.5%), were evaluated during the validation phase to evaluate the proposed BC-FTLLS-TSVM method. The results of the experiment show that the BC-FTLLS-TSVM paradigm procures improved classification of hazard signs in an IoT environment compared to other existing techniques. By leveraging optimized feature selection and fine-tuning through BCOA and FTLLS-TSVM, the proposed method creates effective detection of security threats. The results emphasize the ability of this approach to increase the defense and IoT systems' resistance to emerging cyber threats.

As location-aware IoT (Internet of Things) devices intend to spread across almost every application, IoT devices are going to require different GNSS (Global Navigation Satellite System) receiver design requirements. To deliver on IoT opportunities, system architects and designers need to look carefully at every aspect of system design and architecture to be able to enable the full potential of the IoT era. IoT devices are equipped with different connectivity sensors that can provide a reliable integrated location-awareness solution. IoT devices are mainly relying on GNSS chip to deliver a service when no other RF signal is available. Hence, GNSS chip is expected to maintain a robust and reliable performance even in harsh environment. The harsh environment includes multipath environment, NLOS (Non-Line of Sight) GNSS signal reception, weak GNSS signal power reception, superimposed motion (e.g., arm swing, floating platform fluctuation …etc.), operation under freezing temperature, and interference. The targeted low-cost system design along with the expected harsh operational environment derived us to face exceptional GNSS signal reception condition. This paper discusses lessons learned, and challenges faced signal acquisition, reacquisition, and tracking for several IoT applications. Different operational modes are also explored to accommodate various use cases scenarios for several IoT applications. These different power consumption operational modes allow the GNSS chip to achieve an Ultra-low power consumption which indeed required for IoT applications. This paper provides an overview about the addressed GNSS chip fabricated in a 28nm FD-SOI process. We demonstrate a system performance and power consumption comparison of this chip along with other state-of-the-art GNSS chip. We compare the positioning performance for this device alongside another state-of-the-art GNSS modules and Novatel’s tightly coupled GNSS/INS (Inertial Navigation System) reference solution at numerous scenarios ranging from walking, running, and driving at several sites under different environment.

Privacy preserving Internet of Things: From privacy techniques to a blueprint architecture and efficient implementation

The correct implementation and behavior of Internet of Things (IoT) applications are seldom investigated in the literature. This paper shows how the simulation mechanism can be integrated well into an IoT application development platform for correct implementation and behavior investigation. We use an IoT application development platform called IoTtalk as an example to describe how the simulation mechanism called SimTalk can be built into this IoT platform. We first elaborate on how to implement the simulator for an input IoT device (a sensor). Then we describe how an output IoT device (an actuator) can be simulated by an animated simulator. We use a smart farm application to show how the simulated sensors are used for correct implementation. We use applications including interactive art (skeleton art and water dance) and the pendulum physics experiment as examples to illustrate how IoT application behavior investigation can be achieved in SimTalk. As the main outcome of this paper, the SimTalk simulation codes can be directly reused for real IoT applications. Furthermore, SimTalk is integrated well with an IoT application verification tool in order to formally verify the IoT application configuration. Such features have not been found in any IoT simulators in the world.

The ability to deploy such systems throughout a region, or perhaps a nation, will increase as IoT infrastructure develops. Although Internet of Things (IoT) devices are capable of offering intelligent services, the massive amounts of data they gather and analyze pose a severe security threat. Researchers have spent a lot of work building sophisticated NIDS to prevent the exploitation of IoT data in smart applications. However, present methods may be vulnerable to attack, particularly new attacks, due to a lack of sufficient and evenly distributed attack data used to train the detection strategy. This study introduces a original hierarchical adversarial attack (HAA) generation strategy, which in turn targets the convolutional neural network-based intrusion detection in IoT devices with a limited budget, and therefore realizes the level-aware black-box adversarial attack approach. To generate adversarial instances with little disturbance, an intelligent approach is developed that relies on a saliency map methodology. To do this, a shadow CNN framework has been constructed. Using a random walk having restart based hierarchical node selection approach, a subset of the targeted IoT network's nodes with the lowest structural strength are selected. The proposed HAA generation technique is evaluated in comparison to three reference methods using the publicly available data set UNSW-SOSR2019. In a comparison of the two most sophisticated convolutional neural network (CNN) designs, GCN and JK-Net, it was shown that the classification accuracy for NIDS in IoT settings may be reduced by more than 30%.

With the advancement of 5G mobile telecommunication, various IoT (Internet of Things) devices communicate massive amounts of data by being connected to wireless networks. Since this wireless communication is vulnerable to hackers via data leakage during communication, the transmitted data should be encrypted through block ciphers to protect the data during communication. In addition, in order to encrypt the massive amounts of data securely, it is essential to apply one of secure mode of operation. Among them, CTR (CounTeR) mode is the most widely used in industrial applications. However, these IoT devices have limited resources of computing and memory compared to typical computers, so that it is challenging to process cryptographic algorithms that have computation-intensive tasks in IoT devices at high speed. Thus, it is required that cryptographic algorithms are optimized in IoT devices. In other words, optimizing cryptographic operations on these IoT devices is not only basic but also an essential effort in order to build secure IoT-based service systems. For efficient encryption on IoT devices, even though several ARX (Add-Rotate-XOR)-based ciphers have been proposed, it still necessary to improve the performance of encryption for smooth and secure IoT services. In this article, we propose the first parallel implementations of CTR mode of ARX-based ciphers: LEA (Lightweight Encryption Algorithm), HIGHT (high security and light weight), and revised CHAM on the ARMv8 platform, a popular microcontroller in various IoT applications. For the parallel implementation, we propose an efficient data parallelism technique and register scheduling, which maximizes the usage of vector registers. Through proposed techniques, we process the maximum amount of encryption simultaneously by utilizing all vector registers. Namely, in the case of HIGHT and revised CHAM-64/128 (resp. LEA, revised CHAM-128/128, and CHAM-128/256), we can execute 48 (resp. 24) encryptions simultaneously. In addition, we optimize the process of CTR mode by pre-computing and using the intermediate value of some initial rounds by utilizing the property that the nonce part of CTR mode input is fixed during encryptions. Through the pre-computation table, CTR mode is optimized up until round 4 in LEA, round 5 in HIGHT, and round 7 in revised CHAM. With the proposed parallel processing technique, our software provides 3.09%, 5.26%, and 9.52% of improved performance in LEA, HIGHT, and revised CHAM-64/128, respectively, compared to the existing parallel works in ARM-based MCU. Furthermore, with the proposed CTR mode optimization technique, our software provides the most improved performance with 8.76%, 8.62%, and 15.87% in LEA-CTR, HIGHT-CTR, and revised CHAM-CTR, respectively. This work is the fastest implementation of CTR mode on ARMv8 architecture to the best of our knowledge.

The Internet of Things (IoT) brings internet connectivity to everyday devices. These devices generate a large volume of information that needs to be transmitted to the nodes running the IoT applications, where they are processed and used to make some output decisions. On the one hand, the quality of these decisions is typically affected by the freshness of the received information, thus requesting frequent updates from the IoT devices. On the other hand, the severe energy, memory, processing, and communication constraints of IoT devices and networks pose limitations in the frequency of sensing and reporting. So, it is crucial to minimize the energy consumed by the device for sensing the environment and for transmitting the update messages, while taking into account the requirements for information freshness. Edge-caching can be effective in reducing the sensing and the transmission frequency; however, it requires a proper refreshing scheme to avoid staleness of information, as IoT applications need timeliness of status updates. Recently, the Age of Information (AoI) metric has been introduced: it is the time elapsed since the generation of the last received update, hence it can describe the timeliness of the IoT application’s knowledge of the process sampled by the IoT device. In this work, we propose a model-driven and AoI-aware optimization scheme for information caching at the network edge. To configure the cache parameters, we formulate an optimization problem that minimizes the energy consumption, considering both the sampling frequency and the average frequency of the requests sent to the device for refreshing the cache, while satisfying an AoI requirement expressed by the IoT application. We apply our caching scheme in an emulated IoT network, and we show that it minimizes the energy cost while satisfying the AoI requirement. We also compare the case in which the proposed caching scheme is implemented at the network edge against the case in which there is not a cache at the network edge. We show that the optimized cache can significantly lower the energy cost of devices that have a high transmission cost because it can reduce the number of transmissions. Moreover, the cache makes the system less sensitive to higher application-request rates, as the number of messages forwarded to the devices depends on the cache parameters.

Elderly population in the Asian countries is increasing at a very fast rate. Lack of healthcare resources and infrastructure in many countries makes the task of provding proper healthcare difficult. Internet of things (IoT) in healthcare can address the problem effectively. Patient care is possible at home using IoT devices. IoT devices are used to collect different types of data. Various algorithms may be used to analyse data. IoT devices are connected to the internet and all the data of the patients with various health reports are available online and hence security issues arise. IoT sensors, IoT communication technologies, IoT gadgets, components of IoT, IoT layers, cloud and fog computing, benefits of IoT, IoT-based algorithms, IoT security issues, and IoT challenges are discussed in the chapter. Nowadays global epidemic COVID19 has demolished the economy and health services of all the countries worldwide. Usefulness of IoT in COVID19-related issues is explained here.

At the current pace of technological advancement, it is evident that IoT (Internet of Things) devices are becoming an inevitable part of daily life. Since the growth rate is exceptional, this situation has led to an alarming rise in concern for security threats and issues in the IoT devices. The purpose of this study is to introduce a novel and well-structured threat-modeling approach which is specifically tailored for IoT devices. Traditional threat models like STRIDE, LINDDUN, CORAS, etc., are effective in software applications. However, these models do not cover every aspect of threats specific to IoT devices. The proposed approach consists of a seven-step threat-modeling process. This methodology also addresses aspects of IoT devices which directly affect the user: Privacy threats; Safety threats; and Malfunction threats (PSM). The mentioned threats cannot be addressed effectively with existing traditional threat-modeling approaches. The proposed threat modeling has been applied to three IoT applications: IoT-based smart home environments; IoT-based garment units; and IoT-based water quality management systems, in order to demonstrate the work’s effectiveness. It was seen that when coupling the proposed methodology with the PSM technique and existing threat modeling methods, threats directly affecting users were also identified. This method increases the performance and effectiveness of threat modeling, which leads to increased mitigation of the identified threats. This also leads to an increase in the security of the devices and environment. The final part of the study presents practical mitigation techniques to eliminate threats in IoT devices.

SummaryRecently, the deployment of novel smart network concepts, such as the Internet of things (IoT) or machine‐to‐machine communication, has gained more attention owing to its role in providing communication among various smart devices. The IoT involves a set of IoT devices (IoTDs) such as actuators and sensors that communicate with IoT applications via IoT gateways without human intervention. The IoTDs have different traffic types with various delay requirements, and we can classify them into two main groups: critical and massive IoTDs. The fundamental promising technology in the IoT is the advanced long‐term evolution (LTE‐A). In the future, the number of IoTDs attempting to access an LTE‐A network in a short period will increase rapidly and, thus, significantly reduce the performance of the LTE‐A network and affect the QoS required by variant IoT traffic. Therefore, efficient resource allocation is required.In this paper, we propose a priority‐based allocation scheme for multiclass service in IoT to efficiently share resources between critical and massive IoTD traffic based on their specific characteristics while protecting the critical IoTDs, which have a higher priority over the massive IoTDs. The performance of the proposed scheme is analyzed using the Geo/G/1 queuing system focusing on QoS guarantees and resource utilization of both critical and massive IoTDs. The distribution of service time of the proposed system is determined and, thus, the average waiting and service times are derived. The results indicate that the performance of the massive IoTDs depends on the data traffic characteristics of the critical IoTDs. Furthermore, the results emphasize the importance of the system delay analysis and demonstrate its effects on IoT configurations.

Due to the rapid growth of the Internet of Things (IoT), researchers have demonstrated various IoT solutions, which are used to interconnect a wide range of IoT devices through the Internet. However, IoT stumbled into vertical silos; the available solutions provide specific IoT infrastructure, devices, protocols, data formats and models. This diversity and heterogeneity lead to interoperability issues. Heterogeneity happens at all IoT layers, especially at the application layer; devices often adopt mutually incompatible application-layer communication protocols to connect devices to IoT services. Furthermore, in order to integrate semantics to raw data, each system uses its one domain-specific ontology to make data more understandable and interpretable by adding semantic annotations. Working in isolation reduces the interoperability among IoT devices and systems, things across domains need to internetwork and collaborate to provide high level IoT services. Therefore, to alleviate the problem of both communication protocol interoperability and semantic interoperability across vertical silos of systems at the application layer, this paper proposes a semantic gateway (SGIoT) that acts as a bridge between heterogeneous sink nodes at the physical level and IoT services. SGIoT enables interconnectivity between communication protocols such as CoAP and MQTT regardless of their communication model, meanwhile it enables semantics integration throu gh cross-domain ontology (CDOnto) for semantic annotation, in order to provide interpretation of messages among IoT applications across domains. Our approach focuses on modularity and extensibility.

Internet of Things (IoT) systems are rightly receiving considerable interest for many real-world applications, from in-body networks to satellite networks. Such a massive-scale system generates a considerable amount of traffic data, making IoT systems a distributed data source generator. For many reasons, such as the functionality of IoT applications and Quality of Service (QoS) provisioning, classifying these traffic data is of high importance. In the last few years, widespread interest has been expressed in applying Machine Learning (ML)-based techniques for Network Traffic Classification (NTC) tasks. However, the traditional centralized learning-based traffic classifiers pose serious challenges, especially in IoT networks. The centralized ML techniques call for collecting a large amount of data from various IoT devices, which in turn introduces data governance and privacy challenges. Furthermore, in the centralized ML, training data need to be transferred to the Cloud, which increases communication cost and latency. To address these problems, we propose Federated Learning (FL) Internet of Things (IoT) Traffic Classifier (FLITC)-a Federated Learning (FL)-based IoT traffic classification method which is based on the Multi-Layer Perception (MLP) neural network and holds the local data unimpaired on IoT devices by sending only the learned parameters to the aggregation server. Our experimental results show that the FLITC beats centralized learning in preserving the privacy of sensitive data and offers a better degree of accuracy at the cost of a longer training time.

This study introduces an innovative, resource-efficient architecture that incorporates advanced technologies to create a lightweight, flexible, and scalable framework for remote and limited data collecting and processing in next-generation Internet of Things (IoT) applications. It specifically proposes an integrated Federated LoRaWAN (LoRA-FL) system that combines hierarchical, privacy-preserving Federated Learning (FL), Knowledge Distillation (KD), and a customised Medium Access Control (MAC) protocol, identified as FCA-LoRa, to address the significant limitations of LoRaWAN networks. These encompass strict duty cycle rules, restricted bandwidth, and energy limitations, elements that conventionally hinder the implementation of intelligent IoT devices in rural or isolated settings. The proposed architecture features a hierarchical FL approach enabling multi-tier Artificial Intelligence (AI) model aggregation across edge nodes, gateways, and a central server. The effectiveness of the proposed system is confirmed by two practical applications, smart agriculture and smart livestock farming, which exemplify standard situations for far-edge intelligence. The results indicate that the distilled model consistently attains over 90% packet delivery success, illustrating the architecture’s capacity to provide scalable and energy-efficient intelligence at the edge. This research addresses a significant gap in previous studies that frequently examine FL, communication optimisation, and model compression independently. This study offers a comprehensive, implementable approach that tackles model scalability, and network-layer issues within a cohesive architecture, enhancing the practical implementation of AI-driven IoT deployments over LoRaWAN.