SANTM: Efficient Self-attention-driven Network for Text Matching

Self-attention mechanisms have recently been embraced for a broad range of text-matching applications. Self-attention model takes only one sentence as an input with no extra information, i.e., one can utilize the final hidden state or pooling. However, text-matching problems can be interpreted either in symmetrical or asymmetrical scopes. For instance, paraphrase detection is an asymmetrical task, while textual entailment classification and question-answer matching are considered asymmetrical tasks. In this article, we leverage attractive properties of self-attention mechanism and proposes an attention-based network that incorporates three key components for inter-sequence attention: global pointwise features, preceding attentive features, and contextual features while updating the rest of the components. Our model follows evaluation on two benchmark datasets cover tasks of textual entailment and question-answer matching. The proposed efficient Self-attention-driven Network for Text Matching outperforms the state of the art on the Stanford Natural Language Inference and WikiQA datasets with much fewer parameters.

Labeling Privacy Protection SVM Using Privileged Information for COVID-19 Diagnosis

Edge/fog computing works at the local area network level or devices connected to the sensor or the gateway close to the sensor. These nodes are located in different degrees of proximity to the user, while the data processing and storage are distributed among multiple nodes. In healthcare applications in the Internet of things, when data is transmitted through insecure channels, its privacy and security are the main issues. In recent years, learning from label proportion methods, represented by inverse calibration (InvCal) method, have tried to predict the class label based on class label proportions in certain groups. For privacy protection, the class label of the sample is often sensitive and invisible. As a compromise, only the proportion of class labels in certain groups can be used in these methods. However, due to their weak labeling scheme, their classification performance is often unsatisfactory. In this article, a labeling privacy protection support vector machine using privileged information, called LPP-SVM-PI, is proposed to promote the accuracy of the classifier in infectious disease diagnosis. Based on the framework of the InvCal method, besides using the proportion information of the class label, the idea of learning using privileged information is also introduced to capture the additional information of groups. The slack variables in LPP-SVM-PI are represented as correcting function and projected into the correcting space so that the hidden information of training samples in groups is captured by relaxing the constraints of the classification model. The solution of LPP-SVM-PI can be transformed into a classic quadratic programming problem. The experimental dataset is collected from the Coronavirus disease 2019 (COVID-19) transcription polymerase chain reaction at Hospital Israelita Albert Einstein in Brazil. In the experiment, LPP-SVM-PI is efficiently applied for COVID-19 diagnosis.

Synergic Deep Learning for Smart Health Diagnosis of COVID-19 for Connected Living and Smart Cities

COVID-19 pandemic has led to a significant loss of global deaths, economical status, and so on. To prevent and control COVID-19, a range of smart, complex, spatially heterogeneous, control solutions, and strategies have been conducted. Earlier classification of 2019 novel coronavirus disease (COVID-19) is needed to cure and control the disease. It results in a requirement of secondary diagnosis models, since no precise automated toolkits exist. The latest finding attained using radiological imaging techniques highlighted that the images hold noticeable details regarding the COVID-19 virus. The application of recent artificial intelligence (AI) and deep learning (DL) approaches integrated to radiological images finds useful to accurately detect the disease. This article introduces a new synergic deep learning (SDL)-based smart health diagnosis of COVID-19 using Chest X-Ray Images. The SDL makes use of dual deep convolutional neural networks (DCNNs) and involves a mutual learning process from one another. Particularly, the representation of images learned by both DCNNs is provided as the input of a synergic network, which has a fully connected structure and predicts whether the pair of input images come under the identical class. Besides, the proposed SDL model involves a fuzzy bilateral filtering (FBF) model to pre-process the input image. The integration of FBL and SDL resulted in the effective classification of COVID-19. To investigate the classifier outcome of the SDL model, a detailed set of simulations takes place and ensures the effective performance of the FBF-SDL model over the compared methods.

Edge Computing to Solve Security Issues for Infectious Disease Intelligence Prevention

Nowadays, with the rapid development of intelligent technology, it is urgent to effectively prevent infectious diseases and ensure people's privacy. The present work constructs the intelligent prevention system of infectious diseases based on edge computing by using the edge computing algorithm, and further deploys and optimizes the privacy information security defense strategy of users in the system, controls the cost, constructs the optimal conditions of the system security defense, and finally analyzes the performance of the model. The results show that the system delay decreases with the increase of power in the downlink. In the analysis of the security performance of personal privacy information, it is found that six different nodes can maintain the optimal strategy when the cost is minimized in the finite time domain and infinite time domain. In comparison with other classical algorithms in the communication field, when the intelligent prevention system of infectious diseases constructed adopts the best defense strategy, it can effectively reduce the consumption of computing resources of edge network equipment, and the prediction accuracy is obviously better than that of other algorithms, reaching 83%. Hence, the results demonstrate that the model constructed can ensure the safety performance and forecast accuracy, and achieve the best defense strategy at low cost, which provides experimental reference for the prevention and detection of infectious diseases in the later period.

Forecasting Trend of Coronavirus Disease 2019 using Multi-Task Weighted TSK Fuzzy System

Artificial intelligence– (AI) based fog/edge computing has become a promising paradigm for infectious disease. Various AI algorithms are embedded in cooperative fog/edge devices to construct medical Internet of Things environments, infectious disease forecast systems, smart health, and so on. However, these systems are usually done in isolation, which is called single-task learning. They do not consider the correlation and relationship between multiple/different tasks, so some common information in the model parameters or data characteristics is lost. In this study, each data center in fog/edge computing is considered as a task in the multi-task learning framework. In such a learning framework, a multi-task weighted Takagi-Sugeno-Kang (TSK) fuzzy system, called MW-TSKFS, is developed to forecast the trend of Coronavirus disease 2019 (COVID-19). MW-TSKFS provides a multi-task learning strategy for both antecedent and consequent parameters of fuzzy rules. First, a multi-task weighted fuzzy c-means clustering algorithm is developed for antecedent parameter learning, which extracts the public information among all tasks and the private information of each task. By sharing the public cluster centroid and public membership matrix, the differences of commonality and individuality can be further exploited. For consequent parameter learning of MW-TSKFS, a multi-task collaborative learning mechanism is developed based on ε-insensitive criterion and L2 norm penalty term, which can enhance the generalization and forecasting ability of the proposed fuzzy system. The experimental results on the real COVID-19 time series show that the forecasting tend model based on multi-task the weighted TSK fuzzy system has a high application value.

A Lossless Data-Hiding based IoT Data Authenticity Model in Edge-AI for Connected Living

Edge computing is an emerging technology for the acquisition of Internet-of-Things (IoT) data and provisioning different services in connected living. Artificial Intelligence (AI) powered edge devices (edge-AI) facilitate intelligent IoT data acquisition and services through data analytics. However, data in edge networks are prone to several security threats such as external and internal attacks and transmission errors. Attackers can inject false data during data acquisition or modify stored data in the edge data storage to hamper data analytics. Therefore, an edge-AI device must verify the authenticity of IoT data before using them in data analytics. This article presents an IoT data authenticity model in edge-AI for a connected living using data hiding techniques. Our proposed data authenticity model securely hides the data source’s identification number within IoT data before sending it to edge devices. Edge-AI devices extract hidden information for verifying data authenticity. Existing data hiding approaches for biosignal cannot reconstruct original IoT data after extracting the hidden message from it (i.e., lossy) and are not usable for IoT data authenticity. We propose the first lossless IoT data hiding technique in this article based on error-correcting codes (ECCs). We conduct several experiments to demonstrate the performance of our proposed method. Experimental results establish the lossless property of the proposed approach while maintaining other data hiding properties.

Towards Communication-Efficient and Attack-Resistant Federated Edge Learning for Industrial Internet of Things

Federated Edge Learning (FEL) allows edge nodes to train a global deep learning model collaboratively for edge computing in the Industrial Internet of Things (IIoT), which significantly promotes the development of Industrial 4.0. However, FEL faces two critical challenges: communication overhead and data privacy. FEL suffers from expensive communication overhead when training large-scale multi-node models. Furthermore, due to the vulnerability of FEL to gradient leakage and label-flipping attacks, the training process of the global model is easily compromised by adversaries. To address these challenges, we propose a communication-efficient and privacy-enhanced asynchronous FEL framework for edge computing in IIoT. First, we introduce an asynchronous model update scheme to reduce the computation time that edge nodes wait for global model aggregation. Second, we propose an asynchronous local differential privacy mechanism, which improves communication efficiency and mitigates gradient leakage attacks by adding well-designed noise to the gradients of edge nodes. Third, we design a cloud-side malicious node detection mechanism to detect malicious nodes by testing the local model quality. Such a mechanism can avoid malicious nodes participating in training to mitigate label-flipping attacks. Extensive experimental studies on two real-world datasets demonstrate that the proposed framework can not only improve communication efficiency but also mitigate malicious attacks while its accuracy is comparable to traditional FEL frameworks.

MEC-Based Jamming-Aided Anti-Eavesdropping with Deep Reinforcement Learning for WBANs

Wireless body area network (WBAN) suffers secure challenges, especially the eavesdropping attack, due to constraint resources. In this article, deep reinforcement learning (DRL) and mobile edge computing (MEC) technology are adopted to formulate a DRL-MEC-based jamming-aided anti-eavesdropping (DMEC-JAE) scheme to resist the eavesdropping attack without considering the channel state information. In this scheme, a MEC sensor is chosen to send artificial jamming signals to improve the secrecy rate of the system. Power control technique is utilized to optimize the transmission power of both the source sensor and the MEC sensor to save energy. The remaining energy of the MEC sensor is concerned to ensure routine data transmission and jamming signal transmission. Additionally, the DMEC-JAE scheme integrates with transfer learning for a higher learning rate. The performance bounds of the scheme concerning the secrecy rate, energy consumption, and the utility are evaluated. Simulation results show that the DMEC-JAE scheme can approach the performance bounds with high learning speed, which outperforms the benchmark schemes.

Analysis of Trending Topics and Text-based Channels of Information Delivery in Cybersecurity

Computer users are generally faced with difficulties in making correct security decisions. While an increasingly fewer number of people are trying or willing to take formal security training, online sources including news, security blogs, and websites are continuously making security knowledge more accessible. Analysis of cybersecurity texts from this grey literature can provide insights into the trending topics and identify current security issues as well as how cyber attacks evolve over time. These in turn can support researchers and practitioners in predicting and preparing for these attacks. Comparing different sources may facilitate the learning process for normal users by creating the patterns of the security knowledge gained from different sources. Prior studies neither systematically analysed the wide range of digital sources nor provided any standardisation in analysing the trending topics from recent security texts. Moreover, existing topic modelling methods are not capable of identifying the cybersecurity concepts completely and the generated topics considerably overlap. To address this issue, we propose a semi-automated classification method to generate comprehensive security categories to analyse trending topics. We further compare the identified 16 security categories across different sources based on their popularity and impact. We have revealed several surprising findings as follows: (1) The impact reflected from cybersecurity texts strongly correlates with the monetary loss caused by cybercrimes, (2) security blogs have produced the context of cybersecurity most intensively, and (3) websites deliver security information without caring about timeliness much.