A Comprehensive Machine Learning Framework for Robust Security Management in Cloud-based Internet of Things Systems

A comparative analysis of various machine learning methods for anomaly detection in cyber attacks on IoT networks

LoRaWAN based internet of things (IoT) system for precision irrigation in plasticulture fresh-market tomato

Federated Learning (FL, or Collaborative Learning (CL)) has surely gained a reputation for not only building Machine Learning (ML) models that rely on distributed datasets, but also for starting to play a key role in security and privacy solutions to protect sensitive data and information from a variety of ML-related attacks. This made it an ideal choice for emerging networks such as Internet of Things (IoT) systems, especially with its state-of-the-art algorithms that focus on their practical use over IoT networks, despite the presence of resource-constrained devices. However, the heterogeneous nature of the current devices and models in complex IoT networks has seriously hindered the FL training process's ability to perform well. Thus, rendering it almost unsuitable for direct deployment over IoT networks despite ongoing efforts to tackle this issue and overcome this challenging obstacle. As a result, the main characteristics of FL in the IoT from both security and privacy aspects are presented in this study. We broaden our research to investigate and analyze cutting-edge FL algorithms, models, and protocols, with a focus on their efficacy and practical application across IoT networks and systems alike. This is followed by a comparative analysis of the recently available protection solutions for FL that can be based on cryptographic and non-cryptographic solutions over heterogeneous, dynamic IoT networks. Moreover, the proposed work provides a list of suggestions and recommendations that can be applied to enhance the effectiveness of the adoption of FL and to achieve higher robustness against attacks, especially in heterogeneous dynamic IoT networks and in the presence of resource-constrained devices.

Herein, an Internet of Things (IoT) system with remote reconfigurable wireless sensor network (WSN) nodes is presented and its application to measure group work activity in a classroom is discussed. This IoT system consists of wiki pages, bots, (defined as remotely controlled devices), gateways, and remotely reconfigurable WSN Nodes. The bots/gateways and WSN nodes of the IoT system are controlled by scripts written on wiki pages that are read by the bot/gateways, which then forward the commands contained in the scripts to the WSN nodes. Each WSN node then executes the commands, obtains the resulting sensor values, and then returns those values to the bot/gateways. The bot/gateways relay the values and write them onto the wiki page. Each WSN node is flexible and reconfigurable because its behavior can be changed by the script commands written onto the wiki page. Using this IoT system, we created a measurement system to evaluate activity levels of group work in a classroom. After developing the measurement system, we found it was possible to adjust the sampling rate for obtaining sensor values simply by rewriting the script on the wiki page without directly manipulating the WSN.

IoT data analytics in dynamic environments: From an automated machine learning perspective

Since the Internet of Things (IoT) will be entwined with everything we use in our daily life, the consequence of security flaws escalates. Smart objects will govern most of the home appliances and car engines yielding potential disaster scenarios. In this context, successful attacks could lead to chaos and scary scenarios (www.darkreading.com). Unprotected personal information may expose sensitive and embarrassing data to the public and attacks may threaten not only our computers and smart devices, but our intimacy and perhaps our lives too. Because persons and objects will be bonded with each other, user consent becomes critical. Therefore, thing, object, and user Identity will be the focus of future IoT security solutions, yielding a Trust, Security, and Privacy (TSP) paradigm, which may constitute the Achilles' heel of IoT. While security issues are quite straightforward, mainly from background knowledge, privacy issues are far more complex. Privacy constitutes a rather challenging task, even for the m...

A survey of trust computation models for service management in internet of things systems

Privacy preservation in blockchain based IoT systems: Integration issues, prospects, challenges, and future research directions

Internet of Things (IoT) systems are characterized by being highly heterogeneous, distributed, and scalable, made up of a variety of devices that operate in uncertain and ubiquitous settings. In this sense, models@runtime emerges as a promising software development approach to address IoT systems’ intrinsic characteristics. This study presents a systematic review to know the state of the art using of models@runtime to support IoT systems’ operation. The methodology proposed by Kitchenham has been used to carry out this research. The systematic review answers the following research questions: i) How are models@runtime being used in the IoT domain? And ii) How is addressed the research in studies related to the use of models@runtime in the IoT domain? Initially, 692 primary studies were retrieved, where 50 relevant studies related to approaches based on models@runtime for IoT were selected after applying the corresponding inclusion and exclusion criteria. Those primary studies were classified based on the extraction criteria. Among review’s main results are that the models@runtime have been widely used to support the monitoring and self-adaptation mechanisms in IoT systems, as opposed to the few studies found aimed at interoperability, quality assurance, self-organization, and self-optimization of IoT systems, consisting of essential research opportunities.

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.

This paper presents an implementation of a Wireless Internet of Things (IoT) system applied to the traction motor drive condition monitoring in electric vehicles (EVs). The design and testing of the prototype using an ESP8266 microcontroller module to acquire motor's vibration, current, and temperature information for the motor condition monitoring application is presented. This IoT system has been designed and developed from the ground up using commercially off-the-shelf components and open-source software platform for fast, reliable data acquisitions, low power consumption, and data gathered by the IoT system get reported to the cloud server in real time. The experimental results reveal that the IoT system is capable of capturing and reporting vital motor's parameters to cloud server and an automatic notification is sent to operators when motor's abnormality is detected in real time. Thanks to IoT technology, the preventive maintenance of traction motor can be effectively and remotely planned with rich data collection and analysis. With advanced power consumption reduction techniques, a sensor node consumes extremely low amount of battery power at which ideal for mobile applications.

This chapter discusses the architecture of Internet of Things (IoT) systems. IoT system security takes a team of experts in network security, computer security, hardware and software security, cloud infrastructure security, secure protocols, and cryptography. The security of an IoT system is extremely complex and crosses many security disciplines. Various industries and standards groups have developed and proliferated system architectures in order to better communicate the issues and requirements relating to systems for which they are concerned. The Internet of Things community is no different from any other architectural community. The primary difference is that IoT spans many different industries and ecosystems, and has a diverse set of concerns. The cloud is essential to an IoT system because it houses centralized applications and contains the data model of the IoT system, making those applications accessible to its users wherever they are, and is wholly independent of the actual location of the IoT devices themselves.

The growth of the Internet of Things (IoT) and smart systems has paved the way for the integration of machine learning (ML) and optimization techniques to enhance their efficiency, security, and scalability. This survey provides a comprehensive overview of recent advancements in applying machine learning algorithms and optimization strategies to IoT and smart systems. It highlights key areas where these technologies intersect, such as energy efficiency, intelligent decision-making, resource management, and anomaly detection. The paper discusses various machine learning approaches, including deep learning, reinforcement learning, and supervised/unsupervised models, that have been applied to optimize system performance in real-time applications. Furthermore, the survey examines optimization techniques like metaheuristics, evolutionary algorithms, and gradient-based methods that improve IoT systems' reliability and resource utilization. The integration of these techniques offers significant advantages, including reduced latency, enhanced security, and increased adaptability in smart systems. The findings emphasize the importance of adopting ML and optimization methods to address the challenges posed by the growing complexity of IoT environments, fostering future innovations in connected and autonomous systems. This survey serves as a resource for researchers and practitioners seeking to explore the synergies between IoT, ML, and optimization techniques.

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.

Advanced digital signatures for preserving privacy and trust management in hierarchical heterogeneous IoT: Taxonomy, capabilities, and objectives