Biblio

In this decade, digital transactions have risen exponentially demanding more reliable and secure authentication systems. CAPTCHA (Completely Automated Public Turing Test to tell Computers and Humans Apart) system plays a major role in these systems. These CAPTCHAs are available in character sequence, picture-based, and audio-based formats. It is very essential that these CAPTCHAs should be able to differentiate a computer program from a human precisely. This work tests the strength of text-based CAPTCHAs by breaking them using an algorithm built on CNN (Convolution Neural Network) and RNN (Recurrent Neural Network). The algorithm is designed in such a way as an attempt to break the security features designers have included in the CAPTCHAs to make them hard to be cracked by machines. This algorithm is tested against the synthetic dataset generated in accordance with the schemes used in popular websites. The experiment results exhibit that the model has shown a considerable performance against both the synthetic and real-world CAPTCHAs.

On the Internet of Battlefield Things (IoBT), unmanned aerial vehicles (UAVs) provide significant operational advantages. However, the exploitation of the UAV by an untrustworthy entity might lead to security violations or possibly the destruction of crucial IoBT network functionality. The IoBT system has substantial issues related to data tampering and fabrication through illegal access. This paper proposes the use of an intelligent architecture called IoBT-Net, which is built on a convolution neural network (CNN) and connected with blockchain technology, to identify and trace illicit UAV in the IoBT system. Data storage on the blockchain ledger is protected from unauthorized access, data tampering, and invasions. Conveniently, this paper presents a low complexity and robustly performed CNN called LRCANet to estimate AOA for object localization. The proposed LRCANet is efficiently designed with two core modules, called GFPU and stacks, which are cleverly organized with regular and point convolution layers, a max pool layer, and a ReLU layer associated with residual connectivity. Furthermore, the effectiveness of LRCANET is evaluated by various network and array configurations, RMSE, and compared with the accuracy and complexity of the existing state-of-the-art. Additionally, the implementation of tailored drone-based consensus is evaluated in terms of three major classes and compared with the other existing consensus.

Protection of private and sensitive information is the most alarming issue for security providers in surveillance videos. So to provide privacy as well as to enhance secrecy in surveillance video without affecting its efficiency in detection of violent activities is a challenging task. Here a steganography based algorithm has been proposed which hides private information inside the surveillance video without affecting its accuracy in criminal activity detection. Preprocessing of the surveillance video has been performed using Tunable Q-factor Wavelet Transform (TQWT), secret data has been hidden using Discrete Wavelet Transform (DWT) and after adding payload to the surveillance video, detection of criminal activities has been conducted with maintaining same accuracy as original surveillance video. UCF-crime dataset has been used to validate the proposed framework. Feature extraction is performed and after feature selection it has been trained to Temporal Convolutional Network (TCN) for detection. Performance measure has been compared to the state-of-the-art methods which shows that application of steganography does not affect the detection rate while preserving the perceptual quality of the surveillance video.

In defense and security applications, detection of moving target direction is as important as the target detection and/or target classification. In this study, a methodology for the detection of different mobile targets as approaching or receding was proposed for ground surveillance radar data, and convolutional neural networks (CNN) based on transfer learning were employed for this purpose. In order to improve the classification performance, the use of two key concepts, namely Deep Convolutional Generative Adversarial Network (DCGAN) and decision fusion, has been proposed. With DCGAN, the number of limited available data used for training was increased, thus creating a bigger training dataset with identical distribution to the original data for both moving directions. This generated synthetic data was then used along with the original training data to train three different pre-trained deep convolutional networks. Finally, the classification results obtained from these networks were combined with decision fusion approach. In order to evaluate the performance of the proposed method, publicly available RadEch dataset consisting of eight ground target classes was utilized. Based on the experimental results, it was observed that the combined use of the proposed DCGAN and decision fusion methods increased the detection accuracy of moving target for person, vehicle, group of person and all target groups, by 13.63%, 10.01%, 14.82% and 8.62%, respectively.

Aiming at the prevention of information security risk in protection and control of smart substation, a multi-level security defense method of substation based on data aggregation and convolution neural network (CNN) is proposed. Firstly, the intelligent electronic device(IED) uses "digital certificate + digital signature" for the first level of identity authentication, and uses UKey identification code for the second level of physical identity authentication; Secondly, the device group of the monitoring layer judges whether the data report is tampered during transmission according to the registration stage and its own ID information, and the device group aggregates the data using the credential information; Finally, the convolution decomposition technology and depth separable technology are combined, and the time factor is introduced to control the degree of data fusion and the number of input channels of the network, so that the network model can learn the original data and fused data at the same time. Simulation results show that the proposed method can effectively save communication overhead, ensure the reliable transmission of messages under normal and abnormal operation, and effectively improve the security defense ability of smart substation.

This work analyzed the coding gain that is provided in 6LoWPAN transceivers when channel-coding methods are used. There were made improvements at physical layer of 6LoWPAN technology in the system suggested. Performance analysis was performed using turbo, LDPC and convolutional codes on IEEE 802.15.4 standard that is used in the relevant physical layer. Code rate of convolutional and turbo codes are set to 1/3 and 1/4. For LDPC codes, the code rate is set as 3/4 and 5/6. According to simulation results obtained from the MATLAB environment, turbo codes give better results than LDPC and convolutional codes. It is seen that an average of 3 dB to 8 dB gain is achieved in turbo codes, in LDPC and convolutional coding, it is observed that the gain is between 2 dB and 6 dB depending on the modulation type and code rate.

In this paper, we present a flexible Variable Precision Computation Array (VPCA) component for different accelerators, which leverages a sparsification scheme for activations and a low bits serial-parallel combination computation unit for improving the efficiency and resiliency of accelerators. The VPCA can dynamically decompose the width of activation/weights (from 32bit to 3bit in different accelerators) into 2-bits serial computation units while the 2bits computing units can be combined in parallel computing for high throughput. We propose an on-the-fly compressing and calculating strategy SLE-CLC (single lane encoding, cross lane calculation), which could further improve performance of 2-bit parallel computing. The experiments results on image classification datasets show VPCA can outperforms DaDianNao, Stripes, Loom-2bit by 4.67×, 2.42×, 1.52× without other overhead on convolution layers.

Image style transfer refers to the transformation of the style of image, so that the image details are retained to the maximum extent while the style is transferred. Aiming at the problem of low clarity of style transfer images generated by CycleGAN network, this paper improves the CycleGAN network. In this paper, the network model of auto-encoder and variational auto-encoder is added to the structure. The encoding part of the auto-encoder is used to extract image content features, and the variational auto-encoder is used to extract style features. At the same time, the generating network of the model in this paper uses first to adjust the image size and then perform the convolution operation to replace the traditional deconvolution operation. The discriminating network uses a multi-scale discriminator to force the samples generated by the generating network to be more realistic and approximate the target image, so as to improve the effect of image style transfer.

Today, the Internet covers worldwide. All over the world, people prefer an E-commerce platform to buy or sell their products. Therefore, cybercrime has become the center of attraction for cyber attackers in cyberspace. Phishing is one such technique where the unidentified structure of the Internet has been used by attackers/criminals that intend to deceive users with the use of the illusory website and emails for obtaining their credentials (like account numbers, passwords, and PINs). Consequently, the identification of a phishing or legitimate web page is a challenging issue due to its semantic structure. In this paper, a phishing detection system is implemented using deep learning techniques to prevent such attacks. The system works on URLs by applying a convolutional neural network (CNN) to detect the phishing webpage. In paper [19] the proposed model has achieved 97.98% accuracy whereas our proposed system achieved accuracy of 98.00% which is better than earlier model. This system doesn’t require any feature engineering as the CNN extract features from the URLs automatically through its hidden layers. This is other advantage of the proposed system over earlier reported in [19] as the feature engineering is a very time-consuming task.

Previous research on frequency hopping (FH) signal recognition utilizing deep learning only focuses on single-label signal, but can not deal with overlapped FH signal which has multi-labels. To solve this problem, we propose a new FH signal recognition method based on fully convolutional networks (FCN). Firstly, we perform the short-time Fourier transform (STFT) on the collected FH signal to obtain a two-dimensional time-frequency pattern with time, frequency, and intensity information. Then, the pattern will be put into an improved FCN model, named FH-FCN, to make a pixel-level prediction. Finally, through the statistics of the output pixels, we can get the final classification results. We also design an algorithm that can automatically generate dataset for model training. The experimental results show that, for an overlapped FH signal, which contains up to four different types of signals, our method can recognize them correctly. In addition, the separation of multiple FH signals can be achieved by a slight improvement of our method.

In this conceptual work, we present Deep Convolutional Gaussian Mixture Models (DCGMMs): a new formulation of deep hierarchical Gaussian Mixture Models (GMMs) that is particularly suitable for describing and generating images. Vanilla (i.e., flat) GMMs require a very large number of components to describe images well, leading to long training times and memory issues. DCGMMs avoid this by a stacked architecture of multiple GMM layers, linked by convolution and pooling operations. This allows to exploit the compositionality of images in a similar way as deep CNNs do. DCGMMs can be trained end-to-end by Stochastic Gradient Descent. This sets them apart from vanilla GMMs which are trained by Expectation-Maximization, requiring a prior k-means initialization which is infeasible in a layered structure. For generating sharp images with DCGMMs, we introduce a new gradient-based technique for sampling through non-invertible operations like convolution and pooling. Based on the MNIST and FashionMNIST datasets, we validate the DCGMMs model by demonstrating its superiority over flat GMMs for clustering, sampling and outlier detection.

In view of the problem that the convolution neural network research of facial expression recognition ignores the internal relevance of the key links, which leads to the low accuracy and speed of facial expression recognition, and can't meet the recognition requirements, a series cascade algorithm model for expression recognition of educational robot is constructed and enables the educational robot to recognize multiple students' facial expressions simultaneously, quickly and accurately in the process of movement, in the balance of the accuracy, rapidity and stability of the algorithm, based on the cascade convolution neural network model. Through the CK+ and Oulu-CASIA expression recognition database, the expression recognition experiments of this algorithm are compared with the commonly used STM-ExpLet and FN2EN cascade network algorithms. The results show that the accuracy of the expression recognition method is more than 90%. Compared with the other two commonly used cascade convolution neural network methods, the accuracy of expression recognition is significantly improved.

With the development of artificial intelligence, facial expression recognition (FER) has greatly improved performance in deep learning, but there is still a lot of room for improvement in the study of combining attention to focus the network on key parts of the face. For facial expression recognition, this paper designs a network model, which use spatial transformer network to transform the input image firstly, and then adding channel attention and spatial attention to the convolutional network. In addition, in this paper, the GELU activation function is used in the convolutional network, which improves the recognition rate of facial expressions to a certain extent.

Aiming at the problems of the traditional convolutional neural network (CNN), such as too many parameters, single scale feature and inefficiency by some useless features, a lightweight multi-scale network with attention is proposed for facial expression recognition. The network uses the lightweight convolutional neural network model Xception and combines with the convolutional block attention module (CBAM) to learn key facial features; In addition, depthwise separable convolution module with convolution kernel of 3 × 3, 5 × 5 and 7 × 7 are used to extract features of facial expression image, and the features are fused to expand the receptive field and obtain more rich facial feature information. Experiments on facial expression datasets Fer2013 and KDEF show that the expression recognition accuracy is improved by 2.14% and 2.18% than the original Xception model, and the results further verify the effectiveness of our methods.

Based on the structure of turbo-polar codes, a secure symmetric encryption scheme is proposed to enhance information transmission security in this paper. This scheme utilizes interleaving at information bits and puncturing at parity bits for several times in the encoder. Correspondingly, we need to do the converse interleaving and fill zeros accurately at punctured position. The way of interleaving and puncturing is controlled by the private key of symmetric encryption, making sure the security of the system. The security of Secure Turbo-Polar Codes (STPC) is analyzed at the end of this paper. Simulation results are given to shown that the performance and complexity of Turbo-Polar Codes have little change after symmetric encryption. We also investigate in depth the influence of different remaining parity bit ratios on Frame Error Rate (FER). At low Signal to Noise Rate (SNR), we find it have about 0.6dB advantage when remaining parity bit ratio is between 1/20 and 1/4.

Accidents in Nuclear Power Plants (NPPs) can occur for a variety of causes. However, among these, the scale of accidents due to human error can be greater than expected. Accordingly, researches are being actively conducted using artificial intelligence to reduce human error. Most of the research shows high performance based on the numerical data on NPPs, but the expandability of researches using only numerical data is limited. Therefore, in this study, abnormal diagnosis was performed using artificial intelligence based on image data. The methods applied to abnormal diagnosis are the deep neural network, convolution neural network, and convolution recurrent neural network. Consequently, in nuclear power plants, it is expected that the application of more methodologies can be expanded not only in numerical data but also in image-based data.

Following review depicts a unique speech recognition technique, based on planned analysis and utilization of Neural Network and Google API using speech’s characteristics. Multifactor security system pioneered for the authentication of vocal modalities and identification. Undergone project drives completely unique strategy of independent convolution layers structure and involvement of totally unique convolutions includes spectrum and Mel-frequency cepstral coefficient. This review takes in the statistical analysis of sound using scaled up and scaled down spectrograms, conjointly by exploitation the Google Speech-to-text API turns speech to pass code, it will be cross-verified for extended security purpose. Our study reveals that the incorporated methodology and the result provided elucidate the inclination of research in this area and encouraged us to advance in this field.

Art is the perfect way for people to express their emotions in a way that words are unable to do. By simply looking at art, we can understand a person’s creativity and thoughts. In former times, artists spent a great deal of time creating an image of varied styles. In the current deep learning era, we are able to create images of different styles as we prefer within a short period of time. Neural style transfer is the most popular and widely used deep learning application that applies the desired style to the content image, which in turn generates an output image that is a combination of both style and the content of the original image. In this paper we have implemented the neural style transfer model with two architectures namely Vgg19 and Alexnet. This paper compares the output-styled image and the total loss obtained through VGG19 and Alexnet architectures. In addition, three different activation functions are used to compare quality and total loss of output styled images within Alexnet architectures.

Mathematical morphology has been explored in deep learning architectures, as a substitute to convolution, for problems like pattern recognition and object detection. One major advantage of using morphology in deep learning is the utility of morphological erosion and dilation. Specifically, these operations naturally embody interpretability due to their underlying connections to the analysis of geometric structures. While the use of these operations results in explainable learned filters, morphological deep learning lacks attribution modeling, i.e., a paradigm to specify what areas of the original observed image are important. Furthermore, convolution-based deep learning has achieved attribution modeling through a variety of neural eXplainable Artificial Intelligence (XAI) paradigms (e.g., saliency maps, integrated gradients, guided backpropagation, and gradient class activation mapping). Thus, a problem for morphology-based deep learning is that these XAI methods do not have a morphological interpretation due to the differences in the underlying mathematics. Herein, we extend the neural XAI paradigm of saliency maps to morphological deep learning, and by doing, so provide an example of morphological attribution modeling. Furthermore, our qualitative results highlight some advantages of using morphological attribution modeling.

To deal with the increasingly serious threat of industrial information malicious code, the simulations and characteristics of the domestic security and controllable operating system and office software were implemented in the virtual sandbox environment based on virtualization technology in this study. Firstly, the serialization detection scheme based on the convolution neural network algorithm was improved. Then, the API sequence was modeled and analyzed by the improved convolution neural network algorithm to excavate more local related information of variant sequences. Finally the variant detection of malicious code was realized. Results showed that this improved method had higher efficiency and accuracy for a large number of malicious code detection, and could be applied to the malicious code detection in security and controllable operating system.

Deep Neural Networks (DNNs) have been widely used in variety of fields with great success. However, recent researches indicate that DNNs are susceptible to adversarial attacks, which can easily fool the well-trained DNNs without being detected by human eyes. In this paper, we propose to combine the target DNN model with robust bit plane classifiers to defend against adversarial attacks. It comes from our finding that successful attacks generate imperceptible perturbations, which mainly affects the low-order bits of pixel value in clean images. Hence, using bit planes instead of traditional RGB channels for convolution can effectively reduce channel modification rate. We conduct experiments on dataset CIFAR-10 and GTSRB. The results show that our defense method can effectively increase the model accuracy on average from 8.72% to 85.99% under attacks on CIFAR-10 without sacrificina accuracy of clean images.

Recent advances in adversarial attacks uncover the intrinsic vulnerability of modern deep neural networks. Since then, extensive efforts have been devoted to enhancing the robustness of deep networks via specialized learning algorithms and loss functions. In this work, we take an architectural perspective and investigate the patterns of network architectures that are resilient to adversarial attacks. To obtain the large number of networks needed for this study, we adopt one-shot neural architecture search, training a large network for once and then finetuning the sub-networks sampled therefrom. The sampled architectures together with the accuracies they achieve provide a rich basis for our study. Our ''robust architecture Odyssey'' reveals several valuable observations: 1) densely connected patterns result in improved robustness; 2) under computational budget, adding convolution operations to direct connection edge is effective; 3) flow of solution procedure (FSP) matrix is a good indicator of network robustness. Based on these observations, we discover a family of robust architectures (RobNets). On various datasets, including CIFAR, SVHN, Tiny-ImageNet, and ImageNet, RobNets exhibit superior robustness performance to other widely used architectures. Notably, RobNets substantially improve the robust accuracy ( 5% absolute gains) under both white-box and black-box attacks, even with fewer parameter numbers. Code is available at https://github.com/gmh14/RobNets.

Battery energy storage systems are facing risks of unreliable battery sensor data which might be caused by sensor faults in an embedded battery management system, communication failures, and even cyber-attacks. It is crucial to evaluate the trustworthiness of battery sensor data since inaccurate sensor data could lead to not only serious damages to battery energy storage systems, but also threaten the overall reliability of their applications (e.g., electric vehicles or power grids). This paper introduces a battery sensor data trust framework enabling detecting unreliable data using a deep learning algorithm. The proposed sensor data trust mechanism could potentially improve safety and reliability of the battery energy storage systems. The proposed deep learning-based battery sensor fault detection algorithm is validated by simulation studies using a convolutional neural network.

Nowadays, the networks attacks became very sophisticated and hard to be recognized, The traditional types of intrusion detection systems became inefficient in predicting new types of attacks. As the IDS is an important factor in securing the network in the real time, many new effective IDS approaches have been proposed. In this paper, we intend to discuss different Artificial Neural Networks based IDS approaches, also we are going to categorize them in four categories (normal ANN, DNN, CNN, RNN) and make a comparison between them depending on different performance parameters (accuracy, FNR, FPR, training time, epochs and the learning rate) and other factors like the network structure, the classification type, the used dataset. At the end of the survey, we will mention the merits and demerits of each approach and suggest some enhancements to avoid the noticed drawbacks.

The deep learning-based compressive Sensing (CS) has shown substantial improved performance and in run-time reduction with signal sampling and reconstruction. In most cases, moreover, these techniques suffer from disrupting artefacts or high-frequency contents at low sampling ratios. Similarly, this occurs in the multi-resolution sampling method, which further collects more components with lower frequencies. A promising innovation combining CS with convolutionary neural network has eliminated the sparsity constraint yet recovery persists slow. We propose a Deep wavelet based compressive sensing with multi-resolution framework provides better improvement in reconstruction as well as run time. The proposed model demonstrates outstanding quality on test functions over previous approaches.