Deep Learning Based Security Schemes for IoT Applications: A Review

The Internet of Things (IoT) is widely regarded as a key component of the Internet of the future and thereby has drawn significant interests in recent years. IoT consists of billions of intelligent and communicating “things”, which further extend borders of the world with physical and virtual entities. Such ubiquitous smart things produce massive data every day, posing urgent demands on quick data analysis on various smart mobile devices. Fortunately, the recent breakthroughs in deep learning have enabled us to address the problem in an elegant way. Deep models can be exported to process massive sensor data and learn underlying features quickly and efficiently for various IoT applications on smart devices. In this article, we survey the literature on leveraging deep learning to various IoT applications. We aim to give insights on how deep learning tools can be applied from diverse perspectives to empower IoT applications in four representative domains, including smart healthcare, smart home, smart transportation, and smart industry. A main thrust is to seamlessly merge the two disciplines of deep learning and IoT, resulting in a wide-range of new designs in IoT applications, such as health monitoring, disease analysis, indoor localization, intelligent control, home robotics, traffic prediction, traffic monitoring, autonomous driving, and manufacture inspection. We also discuss a set of issues, challenges, and future research directions that leverage deep learning to empower IoT applications, which may motivate and inspire further developments in this promising field.

The exponential growth of Internet of Things (IoT) has become a transcending force in creating innovative smart devices and connected domains including smart homes, healthcare, transportation and manufacturing. With billions of IoT devices, there is a huge amount of data continuously being generated, transmitted, and stored at various points in the IoT architecture. Deep learning is widely being used in IoT applications to extract useful insights from IoT data. However, IoT users have security and privacy concerns and prefer not to share their personal data with third party applications or stakeholders. In order to address user privacy concerns, Collaborative Deep Learning (CDL) has been largely employed in data-driven applications which enables multiple IoT devices to train their models locally on edge gateways. In this chapter, we first discuss different types of deep learning approaches and how these approaches can be employed in the IoT domain. We present a privacy-preserving collaborative deep learning approach for IoT devices which can achieve benefits from other devices in the system. This learning approach is analyzed from the behavioral perspective of mobile edge devices using a game-theoretic model. We analyze the Nash Equilibrium in N-player static game model. We further present a novel fair collaboration strategy among edge IoT devices using cluster based approach to solve the CDL game, which enforces mobile edge devices for cooperation. We also present implementation details and evaluation analysis in a real-world smart home deployment.

Internet of things (IoT) is a rapidly developing technology that connects various kinds of smart miniature things such as smart medical alert watches, smart vehicles, smart phones, smart running shoes, etc. Smart devices are connected through internet and can communicate to other smart devices in any part of the world in an automated manner. IoT environment often uses constrained devices with low energy, low processing capability, and low memory space. In order to prevent communication failure, a special kind of architecture is needed for IoT. This chapter presents a review of the basic architecture model, communication protocol of IoT, security aspects of IoT, and various IoT applications such as smart agriculture, water management, smart healthcare, smart home, smart industry, and smart vehicles.

The rise of internet connectivity across the globe increases the count of IoT (internet of things)/IIoT (industrial internet of things) devices exponentially. The objects/devices which are connected to the internet are always prone to malicious attacks at various levels, such as physical, network, fog, and applications, which exist in the IoT architecture. Many researchers have addressed this issue and designed their own solutions based on machine and deep learning techniques. It is undeniable that deep learning outperforms machine learning (ML), but it necessitates a massive amount of datasets with appropriate labels. In this work, the deep transfer learning (TL) technique has been adapted for gated recurrent unit (GRU). Each model is trained using a dataset that belongs to one source IoT device (source domain), and this trained model is used to classify the malicious traffic in another dataset that belongs to some other IoT device (target domain). This approach is used for binary classification. These transfer learning models have been evaluated using an IoT/IIoT telemetry dataset called ToN IoT which comprises the sensor data generated from the seven different types of IoT devices. The highest accuracy achieved by IoT garage door was upto 99.76% as a source domain by fixing IoT thermostat as target domain. These models were also evaluated using some more metrics such as precision, recall, F1-measure, training time and testing time. By implementing transfer learning based GRU model, the accuracy of the model is improved from 69.20% to 99.76%. Moreover, to prove the efficiency of the proposed model, it is compared with state of art deep learning model and its results were analyzed in a detailed manner.

Deep Learning for Internet of Things Data Analytics

Continuous growth in software, hardware and internet technology has enabled the growth of internet-based sensor tools that provide physical world observations and data measurement. The Internet of Things(IoT) is made up of billions of smart things that communicate, extending the boundaries of physical and virtual entities of the world further. These intelligent things produce or collect massive data daily with a broad range of applications and fields. Analytics on these huge data is a critical tool for discovering new knowledge, foreseeing future knowledge and making control decisions that make IoT a worthy business paradigm and enhancing technology. Deep learning has been used in a variety of projects involving IoT and mobile apps, with encouraging early results. With its data-driven, anomaly-based methodology and capacity to detect developing, unexpected attacks, deep learning may deliver cutting-edge solutions for IoT intrusion detection. In this paper, the increased amount of information gathered or produced is being used to further develop intelligence and application capabilities through Deep Learning (DL) techniques. Many researchers have been attracted to the various fields of IoT, and both DL and IoT techniques have been approached. Different studies suggested DL as a feasible solution to manage data produced by IoT because it was intended to handle a variety of data in large amounts, requiring almost real-time processing. We start by discussing the introduction to IoT, data generation and data processing. We also discuss the various DL approaches with their procedures. We surveyed and summarized major reporting efforts for DL in the IoT region on various datasets. The features, application and challenges that DL uses to empower IoT applications, which are also discussed in this promising field, can motivate and inspire further developments.

In the era of the Internet of Things (IoT), an enormous amount of sensing devices collect and/or generate various sensory data over time for a wide range of fields and applications. Based on the nature of the application, these devices will result in big or fast/real-time data streams. Applying analytics over such data streams to discover new information, predict future insights, and make control decisions is a crucial process that makes IoT a worthy paradigm for businesses and a quality-of-life improving technology. In this paper, we provide a thorough overview on using a class of advanced machine learning techniques, namely deep learning (DL), to facilitate the analytics and learning in the IoT domain. We start by articulating IoT data characteristics and identifying two major treatments for IoT data from a machine learning perspective, namely IoT big data analytics and IoT streaming data analytics. We also discuss why DL is a promising approach to achieve the desired analytics in these types of data and applications. The potential of using emerging DL techniques for IoT data analytics are then discussed, and its promises and challenges are introduced. We present a comprehensive background on different DL architectures and algorithms. We also analyze and summarize major reported research attempts that leveraged DL in the IoT domain. The smart IoT devices that have incorporated DL in their intelligence background are also discussed. DL implementation approaches on the fog and cloud centers in support of IoT applications are also surveyed. Finally, we shed light on some challenges and potential directions for future research. At the end of each section, we highlight the lessons learned based on our experiments and review of the recent literature.

Energy management solutions in the Internet of Things applications: Technical analysis and new research directions

Introduction to the Special Issue on Evolving IoT and Cyber-Physical Systems: Advancements, Applications, and Solutions

Internet of Things (IoT) has evolved as a revolutionary technology that allows smart devices and sensors to monitor the environment (like smart agriculture, fleet management, smart healthcare, intelligent transportation, etc) wherein they are deployed. Thus, a huge volume of multidimensional data is generated that must be processed promptly for the success of the underlying IoT applications. However, the traditional communication technologies (like TCP/IP) are rigid and limit the scalability of large-scale IoT deployments. Thus, a data-centric framework is required to provide flexible connectivity and data availability for IoT applications. Named Data Network (NDN) is a data-centric network paradigm that does not rely on conventional IP-based technologies and can provide answers to several challenges of IoT applications that are otherwise not resolved by conventional communication technologies. However, it requires an efficient mechanism to handle the large volume of data and store it on the cache of the NDN node. Edge Computing provides the compute (and caching) capability for handling IoT data at a location closer to its origin. Thus, the idea is to utilize the benefits of edge computing and NDN to design an efficient data communication framework. The proposed framework utilizes the edge computing nodes as a cluster head for numerous IoT devices deployed in a specific IoT application (like healthcare). It works as two subsystems, a) a sensor data processing and recommendation system, and b) an NDN-based data storage and delivery system. It was validated using ndnSIM for a hybrid topology concerning the delay, throughput, and packet rate.

The Internet of Things (IoT) era is mainly dependent on the word “Smart”, such as smart cities, smart homes, and smart cars. This aspect can be achieved through the merging of machine learning algorithms with IoT computing models. By adding the Artificial Intelligence (AI) algorithms to IoT, the result is the Cognitive IoT (CIoT). In the automotive industry, many researchers worked on self-diagnosis systems using deep learning, but most of them performed this process on the cloud due to the hardware limitations of the end-devices, and the devices obtain the decision via the cloud servers. Others worked with simple traditional algorithms of machine learning to solve these limitations of the processing capabilities of the end-devices. In this paper, a self-diagnosis smart device is introduced with fast responses and little overhead using the Multi-Layer Perceptron Neural Network (MLP-NN) as a deep learning technique. The MLP-NN learning stage is performed using a Tensorflow framework to generate an MLP model’s parameters. Then, the MLP-NN model is implemented using these model’s parameters on a low cost end-device such as ARM Cortex-M Series architecture. After implementing the MLP-NN model, the IoT implementation is built to publish the decision results. With the proposed implemented method for the smart device, the output decision based on sensors values can be taken by the IoT node itself without returning to the cloud. For comparison, another solution is proposed for the cloud-based architecture, where the MLP-NN model is implemented on Cloud. The results clarify a successful implemented MLP-NN model for little capabilities end-devices, where the smart device solution has a lower traffic and latency than the cloud-based solution.

The role of the Internet of Things (IoT) networks and systems in our daily life cannot be underestimated. IoT is among the fastest evolving innovative technologies that are digitizing and interconnecting many domains. Most life-critical and finance-critical systems are now IoT-based. It is, therefore, paramount that the Quality of Service (QoS) of IoTs is guaranteed. Traditionally, IoTs use heuristic, game theory approaches and optimization techniques for QoS guarantee. However, these methods and approaches have challenges whenever the number of users and devices increases or when multicellular situations are considered. Moreover, IoTs receive and generate huge amounts of data that cannot be effectively handled by the traditional methods for QoS assurance, especially in extracting useful features from this data. Deep Learning (DL) approaches have been suggested as a potential candidate in solving and handling the above-mentioned challenges in order to enhance and guarantee QoS in IoT. In this paper, we provide an extensive review of how DL techniques have been applied to enhance QoS in IoT. From the papers reviewed, we note that QoS in IoT-based systems is breached when the security and privacy of the systems are compromised or when the IoT resources are not properly managed. Therefore, this paper aims at finding out how Deep Learning has been applied to enhance QoS in IoT by preventing security and privacy breaches of the IoT-based systems and ensuring the proper and efficient allocation and management of IoT resources. We identify Deep Learning models and technologies described in state-of-the-art research and review papers and identify those that are most used in handling IoT QoS issues. We provide a detailed explanation of QoS in IoT and an overview of commonly used DL-based algorithms in enhancing QoS. Then, we provide a comprehensive discussion of how various DL techniques have been applied for enhancing QoS. We conclude the paper by highlighting the emerging areas of research around Deep Learning and its applicability in IoT QoS enhancement, future trends, and the associated challenges in the application of Deep Learning for QoS in IoT.

Internet of Things (IoT) deployments have increased drastically based on third-party (fog-assisted architecture) mechanisms to store, process, and share sensor data. IoT environments are mostly vulnerable to security threats due to the lack of intrinsic security measures. Blockchain technology with an untrusty framework to establish trust communication among IoT devices becomes a major concern in lightweight IoT frameworks. To solve this trust issue, we propose a DeepIoT-Block model that combines the consensual deep learning (CDL) technique using the elliptic Diffihelman protocol to strengthen the blockchain-based data storage scheme (BDSS) and Directed Acyclic Graph (DAG) to construct the blockchain network. DeepIoT-Block has implemented using a blockchain system for IoT applications to address storage security issues. DeepIoT-Block guarantees simultaneous computational complexity and transaction efficiency. The performance of the proposed model was verified and validated for IoT-based smart road traffic data. The simulation outcomes show that our proposed model, DeepIoT-Block, is computationally efficient and secure for larger scale IoT applications.

Technologically speaking, humanity lives in an age of evolution, prosperity, and great development, as a new generation of the Internet has emerged; it is the Internet of Things (IoT) which controls all aspects of lives, from the different devices of the home to the large industries. Despite the tremendous benefits offered by IoT, still there are some challenges regarding privacy and information security. The traditional techniques used in Malware Anomaly Detection Systems (MADS) could not give us as robust protection as we need in IoT environments. Therefore, it needed to be replaced with Deep Learning (DL) techniques to improve the MADS and provide the intelligence solutions to protect against malware, attacks, and intrusions, in order to preserve the privacy of users and increase their confidence in and dependence on IoT systems. This research presents a comprehensive study on security solutions in IoT applications, Intrusion Detection Systems (IDS), Malware Detection Systems (MDS), and the role of artificial intelligent (AI) in improving security in IoT.

In this article, we present a comprehensive study with an experimental analysis of federated deep learning approaches for cyber security in the Internet of Things (IoT) applications. Specifically, we first provide a review of the federated learning-based security and privacy systems for several types of IoT applications, including, Industrial IoT, Edge Computing, Internet of Drones, Internet of Healthcare Things, Internet of Vehicles, etc. Second, the use of federated learning with blockchain and malware/intrusion detection systems for IoT applications is discussed. Then, we review the vulnerabilities in federated learning-based security and privacy systems. Finally, we provide an experimental analysis of federated deep learning with three deep learning approaches, namely, Recurrent Neural Network (RNN), Convolutional Neural Network (CNN), and Deep Neural Network (DNN). For each deep learning model, we study the performance of centralized and federated learning under three new real IoT traffic datasets, namely, the Bot-IoT dataset, the MQTTset dataset, and the TON_IoT dataset. The goal of this article is to provide important information on federated deep learning approaches with emerging technologies for cyber security. In addition, it demonstrates that federated deep learning approaches outperform the classic/centralized versions of machine learning (non-federated learning) in assuring the privacy of IoT device data and provide the higher accuracy in detecting attacks.