Physical adversarial attack in artificial intelligence of things

The Internet of Things (IoT) extend the connectivity into billions of IoT devices around the world. Artificial Intelligence (AI) is the best solution to manage huge data flow and storage in IoT network. Nowadays, IoT is becoming more popular with the invention of high internet speed and many advanced sensors that can be integrated into a microcontroller. Internet of Things relies on Artificial Intelligence technology which gives the term of Artificial Intelligence of Things (AIoT). AIoT is transformational and mutually beneficial for both technologies, as AI adds values to IoT through materials and software. This fusion impacts the revolution of industry 4.0 such as maintenance, production chains, optimization and logistics applied in industries to achieve increased productivity, profitability, efficiency, safety, and security.In this paper we will discuss the merge of Artificial Intelligence and Internet of Things, the soft-hard of AIoT and the impact of AIoT on the industry 4.0 applications.

Smart city is a city that increases the interactivity of its components and put emphasis on their functionality. Internet of Things technology (IoT) is an innovative solution in environmental protection. Usually, information on air quality is very scattered. This paper describes the test stages of pre-implementation works, focusing on the presentation of the technical design of the measurement nodes and the assumptions of the IT project. The goal of the project Intelligent Wireless Sensor Network Infrastructure (IIBSC) is, among others, to create a dense network of air quality measurement nodes at city, district or even street level. The concept is based on Internet of Things (IoT) technology using a matrix construction tool connected to multiple identical measurement nodes located in the test area. The project developed a hardware platform supporting sensors and resistant to external factors, and an ISIMPIO information platform based on edge processing technology for processing data from air quality sensors. Due to the use of Internet of Things (IoT) technology, an edge server using edge processing was designed. Edge server provides a complete ecosystem for building edge applications that are fully optimized for seamless field work. In addition, it allows the implementation of integrated Python software, the MQ Telemetry Transport support protocol (MQTT), time-series database, firmware update over a wireless network, and built-in security system. Measuring the concentration of particulate matter and other substances in the air will be useful for specialists assessing their dynamics. The technology and test installation selected corresponds to the leading solutions in this field in Europe and, in the future, should also be extended to less urbanised areas.

When the large amount of Distributed Generations (DGs) are connected to the grid, the whole distributed power network lost line, and the voltage fluctuates are obvious. In recent years, the concepts of power Internet of Things (IoT)technology and energy Internet are proposed. Therefore, power grid technology has entered a new stage. The IoT technology is characterized by high bandwidth, high transmission rate, and low latency. In addition, with the collected data are increased, IoT becomes an effective way to improve the computing power of edge nodes in edge computing. In order to reduce network losses and voltage fluctuations, reactive power optimization is need to be implement in distribution network system. This paper proposes a distributed power voltage regulation strategy based on the particle swarm optimization and deep belief network (PSO-DBN) under the IoT. Firstly, IoT technology and characteristics are introduced, and the current research status of voltage regulation technology are analyzed in distribution network. Secondly, the weight of DBN is improved with PSO. Finally, the IEEE33 bus system is taken as a simulation case, the effects of daily reactive power optimization and the amount of historical data is analyzed. It is concluded that the method proposed in this paper has obvious effects on reducing voltage fluctuation and network loss. KeywordsDistributed generationIoTPSO-DBNReactive power optimization

Internet of Things (IoT) technology has revolutionized modern industrial sectors. Moreover, IoT technology has been incorporated within several vital domains of applicability. However, security is overlooked due to the limited resources of IoT devices. Intrusion detection methods are crucial for detecting attacks and responding adequately to every IoT attack. Conspicuously, the current study outlines a two-stage procedure for the determination and identification of intrusions. In the first stage, a binary classifier termed an Extra Tree (E-Tree) is used to analyze the flow of IoT data traffic within the network. In the second stage, an Ensemble Technique (ET) comprising of E-Tree, Deep Neural Network (DNN), and Random Forest (RF) examines the invasive events that have been identified. The proposed approach is validated for performance analysis. Specifically, Bot-IoT, CICIDS2018, NSL-KDD, and IoTID20 dataset were used for an in-depth performance assessment. Experimental results showed that the suggested strategy was more effective than existing machine learning methods. Specifically, the proposed technique registered enhanced statistical measures of accuracy, normalized accuracy, recall measure, and stability.

We provide an overview of state-of-the-art research and applications in the field of intelligent warehousing based on the Internet of things (IoT) technology in this paper. We summarize and analyze the activities in the warehouse from the application areas, current problems, main technologies, and specific purposes. Then we focus on the challenges of intelligent warehousing and point out the further construction direction of that, which is the collaborative development of IoT, artificial intelligence (AI), cloud computing, and big data technology.

Automatic modulation classification (AMC) using the Deep Neural Network (DNN) approach outperforms the traditional classification techniques, even in the presence of challenging wireless channel environments. However, the adversarial attacks cause the loss of accuracy for the DNN-based AMC by injecting a well-designed perturbation to the wireless channels. In this paper, we propose a novel generative adversarial network (GAN)-based countermeasure approach to safeguard the DNN-based AMC systems against adversarial attack examples. GAN-based aims to eliminate the adversarial attack examples before feeding to the DNN-based classifier. Specifically, we have shown the resiliency of our proposed defense GAN against the Fast-Gradient Sign method (FGSM) algorithm as one of the most potent kinds of attack algorithms to craft the perturbed signals. The existing defense-GAN has been designed for image classification and does not work in our case where the above-mentioned communication system is considered. Thus, our proposed countermeasure approach deploys GANs with a mixture of generators to overcome the mode collapsing problem in a typical GAN facing radio signal classification problem. Simulation results show the effectiveness of our proposed defense GAN so that it could enhance the accuracy of the DNN-based AMC under adversarial attacks to 81%, approximately.

Internet of Things (IoT) technologies are undeniably already all around us, as we stand at the cusp of the next generation of IoT technologies. Indeed, the next-generation of IoT technologies are evolving before IoT technologies have been fully adopted, and smart dust IoT technology is one such example. The concept of smart dust IoT technology, which features very small devices with low computing power, is a revolutionary and innovative concept that enables many things that were previously unimaginable, but at the same time creates unresolved problems. One of the biggest problems is the bottlenecks in data transmission that can be caused by this large number of devices. The bottleneck problem was solved with the Dual Plane Development Kit (DPDK) architecture. However, the DPDK solution created an unexpected new problem, which is called the mixed packet problem. The mixed packet problem, which occurs when a large number of data packets and control packets mix and change at a rapid rate, can slow a system significantly. In this paper, we propose a dynamic partitioning algorithm that solves the mixed packet problem by physically separating the planes and using a learning algorithm to determine the ratio of separated planes. In addition, we propose a training data model eXtended Permuted Frame (XPF) that innovatively increases the number of training data to reflect the packet characteristics of the system. By solving the mixed packet problem in this way, it was found that the proposed dynamic partitioning algorithm performed about 72% better than the general DPDK environment, and 88% closer to the ideal environment.

The Internet of Things (IoT) technology will soon become an integral part of our daily lives to facilitate the control and monitoring of processes and objects and revolutionize the ways that human interact with the physical world. For all features of IoT to become fully functional in practice, there are several obstacles on the way to be surmounted and critical challenges to be addressed. These include, but are not limited to cybersecurity, data privacy, energy consumption and scalability. The Blockchain decentralized nature and its multi-faceted procedures offers a useful mechanism to tackle several of these IoT challenges. However, applying the Blockchain protocols to IoT without considering their tremendous computational loads, delays, and bandwidth overhead can let to a new set of problems. This review evaluates some of the main challenges we face in the integration of Blockchain and IoT technologies and provides insights and high level solutions that can potentially handle the shortcomings and constraints of both IoT and Blockchain technologies.

Deep neural networks are vulnerable to adversarial examples crafted by applying human-imperceptible perturbations on clean inputs. Although many attack methods can achieve high success rates in the white-box setting, they also exhibit weak transferability in the black-box setting. Recently, various methods have been proposed to improve adversarial transferability, in which the input transformation is one of the most effective methods. In this work, we notice that existing input transformation-based works mainly adopt the transformed data in the same domain for augmentation. Inspired by domain generalization, we aim to further improve the transferability using the data augmented from different domains. Specifically, a style transfer network can alter the distribution of low-level visual features in an image while preserving semantic content for humans. Hence, we propose a novel attack method named Style Transfer Method (STM) that utilizes a proposed arbitrary style transfer network to transform the images into different domains. To avoid inconsistent semantic information of stylized images for the classification network, we fine-tune the style transfer network and mix up the generated images added by random noise with the original images to maintain semantic consistency and boost input diversity. Extensive experimental results on the ImageNet-compatible dataset show that our proposed method can significantly improve the adversarial transferability on either normally trained models or adversarially trained models than state-of-the-art input transformation-based attacks. Code is available at: https://github.com/Zhijin-Ge/STM.

The Blockchain technology provides a way to record transactions or any digital interaction that is designed to be secure, tamper-proof, transparent, highly resistant to outages, traceable and auditable. The Internet of Things (IoT) technology is able to link computing devices, mechanical and digital machines, objects, animals or people that are provided with unique identifiers (UIDs) and provides the ability to transfer data over a network without requiring human-to-human or human-to-computer interaction. These features encourage us to explore the combined application of IoT and Blockchain-based technology. In this paper, we propose a system architecture of blockchain and IoT based intellectual property protection system, which can process three types of intellectual property: 1) Patents, Copyrights, Trademarks etc.; 2) Industrial design, Trade dress, Craft works, Trade secrets etc.; and 3) Plant variety rights, Geographical indications etc. Using blockchain P2P network and IoT devices, the system can help us to establish a trusted, self-organized, open and ecological intellectual property protection system. To the best of our knowledge, this is the first work that applying blockchain technology and IoT technology on traditional intellectual property protection and trade ecosystem.

Participation and inclusion in the business ecosystem have emerged as a growing trend for company collaboration in areas such as innovation, product development, and research. Collaborations can take many forms, ranging from the traditional value chain to strategic alliances, corporate networks, and digital ecosystems. The Internet of Things (IoT) and Big Data Analytics (BDA) play key roles in developing smart tourism destinations by delivering efficient management solutions, increased public safety, and improved operational efficiency while managing different risks and challenges, while also being a source of such risks and challenges. The objective of this article was to investigate the potential of IoT and BDA to properly control the risks associated with participants in a tourism destination’s digital ecosystem. The authors used the systematic literature review (SLR) method to examine scientific and applied articles on this subject. As a result, the main risks of the digital tourism ecosystem (DTE) as a whole and of the IoT and BDA technologies used in it were identified and classified; the features of DTE that affect risk management in it were distinguished; IoT technologies and their applications used in DTE were outlined; and the roles of DTE participants and the possible IoT technologies that can successfully address the risks associated with a given role were defined.

The traditional resource sharing method allocates resources according to their importance and node weight ranking, which leads to uneven distribution of node loads and resource allocation with less efficiency and high energy consumption. In order to solve the above problems, the method of resource allocation of college ideological and political education based on Internet of Things (IoT) technology is studied. The IoT technology is used for establishing the communication Internet of Things or for sharing college ideological and political education resources, and the MCTS algorithm is used to search for college ideological and political education resources. For the case of education resources in colleges and universities, according to the simple semantic reasoning for establishing the mapping relationship between education resources and distribution of nodes, we realise the allocation of resources for education. The test experiment results show that the researched resource allocation method has low allocation delay and reduces at least about 23.7% of energy consumption, which is more effective.

This study aims to analyze the use of Internet of Things (IoT) technology in the novel "Hujan" by Tere Liye. This novel shows how the love story and life struggle of the main character, Lail, are connected to the development of IoT technology. This research aims to understand how IoT technology shapes the story from the aspect of the situation to the characteristics of the related IoT devices. Through the hermeneutic method, this research identifies the use of IoT in several contexts. The findings obtained in the novel are 1) Smart Buildings, 2) Smart Farming, 3) Smart Home, 4) Smart City, and 5) Smart Healthcare. The results show that IoT technology is a key element in achieving a more advanced and connected digital society, bringing positive impacts in daily life and providing smart solutions to various global challenges.

Nowadays, monitoring health systems in robust technology has been extensively applied in the sports field. Even though massive utilization of wearable device technologies aims to quantify athlete performance, inconsistent performance still exists between training sessions and competition. The rigorous discussion about the latest research in monitoring technological systems will help trainers obtain accurate data about athlete performance. This paper focuses on the athlete monitoring system in terms of psychological and physiological parameters and applications in individual sports based on Internet of Things (IoT) Technology. The study incorporates three factors: the parameters that affect athlete performance, multiple device sensors in sports health monitoring, and IoT technology’s application for athletes. Based on analysis and observation, efficient sports health monitoring can effectively enhance athlete performance in physiological and psychological conditions. An IoT system encompasses four main aspects: sensing, networking, data processing and application layer. These aspects provide real-time information on the athlete’s body condition during training and games. Therefore, this monitoring system greatly assists coaches in designing practical training and activities for athletes. It is highlighted that wearable health monitoring systems by IoT technology will be further built based on athlete requirements.

Major advances in the Internet of Things (IoT) technologies are offering unprecedented automated services to various sectors. IoT has shown great promise in transforming buildings and institutions into smart buildings and institutions, making traditional task management more efficient. In particular, there has been remarkable progress in successfully integrating IoT into various contexts, such as smart homes, businesses and cities. Success in such technological transformations is not only due to the proper deployment and implementation of IoT but also to the effective employment of related technologies, such as big data and cloud computing technologies, and making informed decisions on the inclusion of the required hardware and software for all the elements involved in the IoT environment. While a significant amount of IoT research in various contexts has been proliferated in recent years, attention given to its deployment for linguistic landscapes (LLs) is still very rare. The aim of this paper is to propose a smart Al-Noor Mall LL which takes into account the appropriate deployment of IoT tools and relevant technologies. The paper also thoroughly discusses the background of the field, covering IoT technologies, cloud computing, and big data studies, followed by a review of the recent publications involving the successful deployment of IoT technologies combined with big data and cloud computing in various contexts. The literature also covers the success factors that contribute to the robustness of the required real-time operating system (RTOS) in an IoT-based environment in order to enable IoT devices to manage their resources efficiently. Based on a detailed analysis of the literature, a three-level framework (i.e. the object, communications and application levels) together with the elements that are required for IoT-based smart LL solutions is proposed. A case study of Al-Noor Mall is used to validate the proposed framework and the results indicate that IBM Bluemix can help Al-Noor Mall management and customers to locate any particular shop in the huge shopping mall, which thereby makes the customers’ shopping experience more satisfying. Finally, the challenges (i.e. energy efficiency, security, and intelligent data analysis) facing the successful deployment of IoT technologies are discussed with proposals for future research directions in the IoT research field.