Abstract

Tables are information-rich structured objects in document images. While significant work has been done in localizing tables as graphic objects in document images, only limited attempts exist on table structure recognition. Most existing literature on structure recognition depends on extraction of meta-features from the pdf document or on the optical character recognition (ocr) models to extract low-level lay- out features from the image. However, these methods fail to generalize well because of the absence of meta-features or errors made by the ocr when there is a significant variance in table layouts and text organization. In our work, we focus on tables that have complex structures, dense con- tent, and varying layouts with no dependency on meta-features and/or ocr. We present an approach for table structure recognition that combines cell detection and interaction modules to localize the cells and predict their row and column associations with other detected cells. We incorporate structural constraints as additional differential components to the loss function for cell detection. We empirically validate our method on the publicly available real-world datasets - icdar-2013, icdar-2019 (ctdar) archival, unlv, scitsr, scitsr-comp, tablebank, and pubtabnet. Our attempt opens up a new direction for table structure recognition by combining top-down (table cells detection) and bottom-up (structure recognition) cues in visually understanding the tables.

Abstract

Current approaches for person recognition train an en- semble of region specific convolutional neural networks for representation learning, and then adopt naive fusion strate- gies to combine their features or predictions during testing. In this paper, we propose an unified end-to-end architec- ture that generates a complete person representation based on pooling and aggregation of features from multiple body regions. Our network takes a person image and the pre- determined locations of body regions as input, and gener- ates common feature maps that are shared across all the re- gions. Multiple features corresponding to different regions are then pooled and combined with an aggregation block, where the adaptive weights required for aggregation are obtained through an attention mechanism. Evaluations on three person recognition datasets - PIPA, Soccer and Han- nah show that a single model trained end-to-end is com- putationally faster, requires fewer parameters and achieves improved performance over separately trained models.

Abstract

Cities having hot weather conditions results in geo- metrical distortion, thereby adversely affecting the perfor- mance of semantic segmentation model. In this work, we study the problem of semantic segmentation model in adapt- ing to such hot climate cities. This issue can be circum- vented by collecting and annotating images in such weather conditions and training segmentation models on those im- ages. But the task of semantically annotating images for every environment is painstaking and expensive. Hence, we propose a framework that improves the performance of semantic segmentation models without explicitly creat- ing an annotated dataset for such adverse weather varia- tions. Our framework consists of two parts, a restoration network to remove the geometrical distortions caused by hot weather and an adaptive segmentation network that is trained on an additional loss to adapt to the statistics of the ground-truth segmentation map. We train our framework on the Cityscapes dataset, which showed a total IoU gain of 12.707 over standard segmentation models. We also ob- serve that the segmentation results obtained by our frame- work gave a significant improvement for small classes such as poles, person, and rider, which are essential and valu- able for autonomous navigation based applications.

Abstract

On the basis of the Internet of Things (IoT) applications, several variants such as Internet of Energy (IoE), Internet of Vehicles (IoV), Internet of Drones (IoD), Internet of Medical Things (Internet of Health, IoMT) and Internet of Intelligent Battlefield Things (IoIBT) are developed. The smart devices involved in IoT can also utilize artificial intelligence algorithm (i.e., machine learning) to make the communication environment more effective and efficient. Intelligent Battlefield Things (IBT) communication environment is an example of that kind. It consists of smart and intelligent devices (i.e., drones), which monitor the activities of the enemies and retaliate accordingly. Hence, we need very less or negligible human involvement. IBT communication environment is very suitable for the purpose of battlefield communication (i.e., war zone, target tracking and hitting, border area surveillance and retaliation). However, IBT has certain drawbacks, because it may be vulnerable to different types of attacks, such as replay, man-in-the-middle, impersonation, data modification, data leakage attacks, etc. Therefore, it becomes essential to provide a security mechanism to secure the communication that happens in IBT environment. To achieve this purpose, we propose a secure communication framework for the blockchain of IBT environment. In addition, the benefits of applications of blockchain of IBT are discussed. The issues and challenges of blockchain of IBT environment are also highlighted. Finally, a security analysis of the proposed framework is conducted to depict its resilience against possible attacks.

Abstract

Internet of Drones (IoD) architecture is designed to support a co-ordinated access for the airspace using the unmanned aerial vehicles (UAVs) known as drones. Recently, IoD communication environment is extremely useful for various applications in our daily activities. Artificial intelligence (AI)-enabled Internet of Things (IoT)-based drone-aided healthcare service is a specialized environment which can be used for different types of tasks, for instance, blood and urine samples collections, medicine delivery and for the delivery of other medical needs including the current pandemic of COVID-19. Due to wireless nature of communication among the deployed drones and their ground station server, several attacks (for example, replay, man-in-the-middle, impersonation and privileged-insider attacks) can be easily mounted by malicious attackers. To protect such attacks, the deployment of effective authentication, access control and key management schemes are extremely important in the IoD environment. Furthermore, combining the blockchain mechanism with deployed authentication make it more robust against various types of attacks. To mitigate such issues, we propose a private-blockchain based framework for secure communication in an IoT-enabled drone-aided healthcare environment. The blockchain-based simulation of the proposed framework has been carried out to measure its impact on various performance parameters.

Abstract

Industrial Internet of Things (IIoT) is a communication environment that consists of various interconnected sensing devices, instruments, and other devices connected together with industrial software tools and applications. The important applications of IIoT include industrial automation, predictive maintenance, smart logistics management, power management, smart package management and smart robotics. However, IIoT may be vulnerable to different types of attacks as the IoT smart devices communicate among each other via insecure communication means. Thus, there is an essential requirement of deployment of secure access control scheme in IIoT environment, which is one of the important security services for securing IIoT. In this paper, we propose a novel access control scheme for fog based IIoT communication, called SAC-FIIoT. We provide the details of network model as well as threat model, which are required to design SAC-FIIoT. The security analysis of SAC-FIIoT shows its resilience against various types of possible attacks. SAC-FIIoT is also compared with other related competing existing schemes and it was found that its performance is better than these competing schemes. Therefore, SAC-FIIoT is suitable for access control in a fog-based IIoT environment.

Abstract

Among the security services, like authentication, access control, key management and intrusion detection, user authentication is very much needed for a smart city environment because an external authorized user may require the real time data to be accessed directly from the deployed Internet of Things (IoT) enabled smart devices. Using the established session key between the user and an access smart device though mutual authentication and key agreement process, the real time data can be securely accessed. To deal with this issue, we propose a new user authentication scheme in smart city environment using three factors of a legal registered user (mobile device, password and biometrics). The proposed scheme is shown to be robust against a number of potential attacks needed in an IoT-based smart city deployment. The simulation study for formal security verification using the widely-accepted “Automated Validation of Internet Security Protocols and Applications (AVISPA)” tool demonstrates that the proposed scheme is also secure. Furthermore, experiments on various cryptographic primitives have been carried out using “MIRACL Cryptographic SDK: Multiprecision Integer and Rational Arithmetic Cryptographic Library” under both server and Raspberry PI 3 settings. Finally, a comprehensive comparative analysis shows the effectiveness and better security of the proposed scheme as compared with other state of art user authentication schemes.

Abstract

The vehicles in Internet of Vehicles (IoV) can be used to opportunistically gather and distribute the data in a smart city environment. However, at the same time, various security threats arise due to insecure communication happening among various entities in an IoV-based smart city deployment. To address this issue, we aim to design a novel blockchain-enabled batch authentication scheme in Artificial Intelligence (AI)-envisioned IoV-based smart city deployment. The latest trends and revolutions in technologies incorporate AI/Machine Learning (ML) in blockchaining to produce a secure, efficient and intelligent blockchain based system. The data stored in the blocks in the blockchain are authentic and genuine, which makes the AI/ML algorithms to work at their exceptions in order produce correct predictions on the blockchain data. Through the signing phase of the proposed scheme, each vehicle in a dynamically formed cluster broadcasts a message to its own member and respective road-side unit (RSU). In the proposed scheme, two types of authentication take place: vehicle to vehicle (V2V) authentication allows a vehicle to authenticate its neighbor vehicles in its cluster, while batch authentication permits a group of cluster vehicles to be authenticated by their . At the end, a group key is established among the vehicles and in their cluster. then gathers securely data from its vehicles and form several transactions including the information of vehicles and its own given information to the cluster member vehicles. The transactions are formed later by the nearby fog server associated with and then by the cloud server to form a complete block. The created blocks are mined by the cloud servers in a Peer-to-Peer (P2P) cloud server network through the voting-based Practical Byzantine Fault Tolerance (PBFT) consensus algorithm. The authentic and genuine data of the blockchain are utilized for Big data analytics through AI/ML algorithms. It is shown that the proposed scheme is highly robust against various attacks through formal and informal security analysis, and also through formal security verification tool. A detailed comparative analysis reveals that the proposed scheme achieves superior security and functionality features, and offers comparable storage, communication and computational costs as compared to other existing competing schemes. Finally, the blockchain implementation has been carried out on the proposed scheme to show its effectiveness.

Abstract

We design a new blockchain-based access control protocol in IoT-enabled smart-grid system, called DBACP-IoTSG. Through the proposed DBACP-IoTSG, the data is securely brought to the service providers from their respectively smart meters. The Peer-to-Peer (P2P) network is formed by the participating services providers, where the peer nodes are responsible for creating the blocks from the gathered data securely from their corresponding smart meters and adding them into the blockchain after validation of the blocks using the voting-based consensus algorithm. In our work, the blockchain is considered as private because the data collected from the consumers of the smart meters are private and confidential. By the formal security analysis under the random oracle model, non-mathematical security analysis and software-based formal security verification, DBACP-IoTSG is shown to be resistant against various attacks. We carry out the experimental results of various cryptographic primitives that are needed for comparative analysis using the widely-used Multiprecision Integer and Rational Arithmetic Cryptographic Library (MIRACL). A detailed comparative study reveals that DBACP-IoTSG supports more functionality features and provides better security apart from its low communication and computation costs as compared to recently proposed relevant schemes. In addition, the blockchain implementation of DBACPIoTSG has been performed to measure computational time needed for the varied number of blocks addition and also the varied number of transactions per block in the blockchain.

Abstract

Telecare medical information system (TMIS) implemented in wireless body area network (WBAN) is convenient and time-saving for patients and doctors. TMIS is realized using wearable devices worn by a patient, and wearable devices generate patient health data and transmit them to a server through a public channel. Unfortunately, a malicious attacker can attempt performing various attacks through such a channel. Therefore, establishing a secure authentication process between a patient and a server is essential. Moreover, wearable devices have limited storage power. Cloud computing can be considered to resolve this problem by providing a storage service in the TMIS environment. In this environment, access control of the patient health data is essential for the quality of healthcare. Furthermore, the database of the cloud server is a major target for an attacker. The attacker can try to modify, forge, or delete the stored data. To resolve these problems, we propose a secure authentication protocol for a cloud-assisted TMIS with access control using blockchain. We employ ciphertext-policy attribute-based encryption (CP-ABE) to establish access control for health data stored in the cloud server, and apply blockchain to guarantee data integrity. To prove robustness of the proposed protocol, we conduct informal analysis and Burrows-Adabi-Needham (BAN) logic analysis, and we formally validate the proposed protocol using automated validation of internet security protocols and applications (AVISPA). Consequently, we show that the proposed protocol provides more security and has better efficiency compared to related protocols. Therefore, the proposed protocol is proper for a practical TMIS environment.