Search

Machine learning (ML) represents one of the main pillars of the current digital era, specifically in modern real-world applications. The Internet of Things (IoT) technology is foundational in developing advanced intelligent systems. The convergence of ML and IoT drives significant advancements across various domains, such as making IoT-based security systems smarter and more efficient. However, ML-based IoT systems are vulnerable to lurking attacks during the training and testing phases. An adversarial attack aims to corrupt the ML model’s functionality by introducing perturbed inputs. Consequently, it can pose significant risks leading to devices’ malfunction, services’ interruption, and personal data misuse. This article examines the severity of adversarial attacks and accentuates the importance of designing secure and robust ML models in the IoT context. A comprehensive classification of adversarial machine learning (AML) is provided. Moreover, a systematic literature review of the latest research trends (from 2020 to 2024) of the intersection of AML and IoT-based security systems is presented. The results revealed the availability of various AML attack techniques, where the Fast Gradient Signed Method (FGSM) is the most employed. Several studies recommend the adversarial training technique to defend against such attacks. Finally, potential open issues and main research directions are highlighted for future consideration and enhancement.

The Internet of Things (IoT) aims to transform everyday physical objects into an interconnected ecosystem with digital data accessible anywhere and anytime. “Things” in IoT are embedded with sensing, processing, and actuating capabilities and cooperate in providing smart and innovative services autonomously. The rapid spread of IoT services arises different security vulnerabilities that need to be carefully addressed. Several emerging and promising technologies and techniques are introduced to improve the security of IoT. This paper aims to provide an up-to-date vision of the current research topics related to IoT security. Initially, we introduce common elements and protocols of IoT to demystify the origins of threats in IoT. Then, we propose a taxonomy of IoT attacks and analyze the security vulnerabilities of IoT at different layers. Subsequently, we provide a comparison of recent security schemes based on emerging solutions including fog computing, edge computing, software-defined networking (SDN), blockchain, lightweight cryptography, homomorphic and searchable encryption, and machine learning. Finally, security challenges are discussed and future directions are highlighted for future interested researchers.

The Internet of Things (IoT) invention has taken the growth of sensors technology to a completely high step. New challenges in terms of data delivery have emerged due to strict QoS conditions. Among the solutions proposed in the literature is the subdivision of the large-scale network into several clusters. Except that most of these solutions are conventional. However, prior research generally confirms that bio-inspired paradigms are more flexible and effective compared to traditional methods. When it comes to a heterogeneous network, additional constraints appear. Nodes have different buffer sizes. Then, data captured must be sent before their buffers are full, otherwise, some data will be lost. This is not suitable for a real-time application where time and information are crucial elements. In this study, a comprehensive overview of the use of sensors in IoT contexts is performed. Two algorithms as Grey Wolf Optimizer (GWO) and Whale Optimization Algorithm (WOA), combined with the Imperialist Competitive Algorithm (ICA) based Cluster Head (CH) selection with a novel approach for heterogeneous networks are proposed. These algorithms can support data exchange over a heterogeneous Wireless Sensor Network (WSN) infrastructure with taking into consideration the buffer overflow problem. Simulation results are presented and discussed in different network designs. The research demonstrated that knowing well how to manage buffers using bio-inspired techniques, leads to a significant reduction in data loss.

A vehicular ad-hoc network (VANET) is the basic block in building an intelligent transportation system that improves the traffic flow and makes needed information conveniently accessible. VANET depends on a dense exchange of sensed data between vehicles and Road Side Units (RSUs). A large amount of sensed data requires a huge computation and storage capabilities, which is provided by the vehicular cloud computing (VCC). However, the security problems of data confidentiality, access control, vehicles’ authentication, and conductors’ privacy in VCC are issues that need to be solved. In this paper, we propose an efficient algorithm to ensure VCC security and privacy. We use Pseudo-ID instead of vehicles’ real ID to provide conductors’ privacy, Identifier-Based Signature mechanism is used to guarantee vehicles’ authentication, and Ciphertext-Policy Attribute-Based Encryption (CP-ABE) algorithm is used for key distribution. Our liGhtweight secURe AutheNticaTion and keY distribution scheme for vehicular cloud computing (GUARANTY) ensures a secure keys distribution to minimize the encryption and decryption computation cost. Vehicles use a symmetrical cryptography in their communication. We analyze the security of our algorithm using AVISPA tool. We use this tool to simulate insiders and outsiders attacks. We evaluate our algorithm’s performance in terms of computation delay and reception rate.

Under a dense and large IoT network, a star topology where each device is directly connected to the Internet gateway may cause serious waste of energy and congestion issues. Grouping network devices into clusters provides a suitable architecture to reduce the energy consumption and allows an effective management of communication channels. Although several clustering approaches were proposed in the literature, most of them use the single-hop intra-clustering model. In a large network, the number of clusters increases and the energy draining remains almost the same as in un-clustered architecture. To solve the problem, several approaches use the k-hop intra-clustering to generate a reduced number of large clusters. However, k-hop proposed schemes are, generally, centralized and only assume the node direct neighbors information which lack of robustness. In this regard, the present work proposes a distributed approach for the k-hop intra-clustering called Distributed Clustering based 2-Hop Connectivity (DC2HC). The algorithm uses the two-hop neighbors connectivity to elect the appropriate set of cluster heads and strengthen the clusters connectivity. The objective is to optimize the set of representative cluster heads to minimize the number of long range communication channels and expand the network lifetime. The paper provides the convergence proof of the proposed solution. Simulation results show that our proposed protocol outperforms similar approaches available in the literature by reducing the number of generated cluster heads and achieving longer network lifetime.

In recent years, technological advances and the ever-increasing power of embedded systems have seen the emergence of so-called smart cities. In these cities, application needs are increasingly calling for Large-Scale Wireless Sensor Networks (LS-WSN). However, the design and implementation of such networks pose several important and interesting challenges. These low-cost, low-power devices are characterized by limited computing, memory storage, communication, and battery power capabilities. Moreover, sensors are often required to cooperate in order to route the collected data to a single central node (or sink). The many-to-one communication model that governs dense and widely deployed Wireless Sensor Networks (WSNs) most often leads to problems of network overload and congestion. Indeed, it is easy to show that the closer a node is geographical to the sink, the more data sources it has to relay. This leads to several problems including overloading of nodes close to the sink, high loss rate in the area close to the sink, and poor distribution of power consumption that directly affects the lives of these networks. In this context, we propose a contribution to the problem of LS-WSN energy consumption. We designed a hierarchical 3-tier architecture of LS-WSNs coupled with a modeling of the activities of the different sensors in the network. This architecture that is based on clustering also includes a redeployment function to maintain the topology in case of coverage gaps. The results of the performed simulations show that our architecture maximizes the lifetime than compared solutions.

Large Scale Wireless Sensor Networks (LS-WSNs) are Wireless Sensor Networks (WSNs) composed of an impressive number of sensors, with inherent detection and processing capabilities, to be deployed over large areas of interest. The deployment of a very large number of diverse or similar sensors is certainly a common practice that aims to overcome frequent sensor failures and avoid any human intervention to replace them or recharge their batteries, to ensure the reliability of the network. However, in practice, the complexity of LS-WSNs pose significant challenges to ensuring quality communications in terms of symmetry of radio links and maximizing network life. In recent years, most of the proposed LS-WSN deployment techniques aim either to maximize network connectivity, increase coverage of the area of interest or, of course, extend network life. Few studies have considered the choice of a good LS-WSN deployment strategy as a solution for both connectivity and energy consumption efficiency. In this paper, we designed a LS-WSN as a tool for collecting big data generated by smart cities. The intrinsic characteristics of big data require the use of heterogeneous sensors. Furthermore, in order to build a heterogeneous LS-WSN, our scientific contributions include a model of quantifying the kinds of sensors in the network and the multi-level architecture for LS-WSN deployment, which relies on clustering for the big data collection. The results simulations show that our proposed LS-WSN architecture is better than some well known WSN protocols in the literature including Low Energy Adaptive Clustering Hierarchy (LEACH), E-LEACH, SEP, DEEC, EECDA, DSCHE and BEENISH.

Data collection is one of the main operations performed in Wireless Sensor Networks (WSNs). Even if several interesting approaches on data collection have been proposed during the last decade, it remains a research focus in full swing with a number of important challenges. Indeed, the continuous reduction in sensor size and cost, the variety of sensors available on the market, and the tremendous advances in wireless communication technology have potentially broadened the impact of WSNs. The range of application of WSNs now extends from health to the military field through home automation, environmental monitoring and tracking, as well as other areas of human activity. Moreover, the expansion of the Internet of Things (IoT) has resulted in an important amount of heterogeneous data that are produced at an exponential rate. Furthermore, these data are of interest to both industry and in research. This fact makes their collection and analysis imperative for many purposes. In view of the characteristics of these data, we believe that very large-scale and heterogeneous WSNs can be very useful for collecting and processing these Big Data. However, the scaling up of WSNs presents several challenges that are of interest in both network architecture to be proposed, and the design of data-routing protocols. This paper reviews the background and state of the art of Big Data collection in Large-Scale WSNs (LS-WSNs), compares and discusses on challenges of Big Data collection in LS-WSNs, and proposes possible directions for the future.