Biblio

Fashion is the way we present ourselves which mainly focuses on vision, has attracted great interest from computer vision researchers. It is generally used to search fashion products in online shopping malls to know the descriptive information of the product. The main objectives of our paper is to use deep learning (DL) and machine learning (ML) methods to correctly identify and categorize clothing images. In this work, we used ML algorithms (support vector machines (SVM), K-Nearest Neirghbors (KNN), Decision tree (DT), Random Forest (RF)), DL algorithms (Convolutionnal Neurals Network (CNN), AlexNet, GoogleNet, LeNet, LeNet5) and the transfer learning using a pretrained models (VGG16, MobileNet and RestNet50). We trained and tested our models online using google colaboratory with Tensorflow/Keras and Scikit-Learn libraries that support deep learning and machine learning in Python. The main metric used in our study to evaluate the performance of ML and DL algorithms is the accuracy and matrix confusion. The best result for the ML models is obtained with the use of ANN (88.71%) and for the DL models is obtained for the GoogleNet architecture (93.75%). The results obtained showed that the number of epochs and the depth of the network have an effect in obtaining the best results.

Detection of malware and security attacks is a complex process that can vary in its details and analysis activities. As part of the detection process, malware scanners try to categorize a malware once it is detected under one of the known malware categories (e.g. worms, spywares, viruses, etc.). However, many studies and researches indicate problems with scanners categorizing or identifying a particular malware under more than one malware category. This paper, and several others, show that machine learning can be used for malware detection especially with ensemble base prediction methods. In this paper, we evaluated several custom-built ensemble models. We focused on multi-label malware classification as individual or classical classifiers showed low accuracy in such territory.This paper showed that recent machine models such as ensemble and deep learning can be used for malware detection with better performance in comparison with classical models. This is very critical in such a dynamic and yet important detection systems where challenges such as the detection of unknown or zero-day malware will continue to exist and evolve.

Android malware is continuously evolving at an alarming rate due to the growing vulnerabilities. This demands more effective malware detection methods. This paper presents DynaMalDroid, a dynamic analysis-based framework to detect malicious applications in the Android platform. The proposed framework contains three modules: dynamic analysis, feature engineering, and detection. We utilized the well-known CICMalDroid2020 dataset, and the system calls of apps are extracted through dynamic analysis. We trained our proposed model to recognize malware by selecting features obtained through the feature engineering module. Further, with these selected features, the detection module applies different Machine Learning classifiers like Random Forest, Decision Tree, Logistic Regression, Support Vector Machine, Naïve-Bayes, K-Nearest Neighbour, and AdaBoost, to recognize whether an application is malicious or not. The experiments have shown that several classifiers have demonstrated excellent performance and have an accuracy of up to 99%. The models with Support Vector Machine and AdaBoost classifiers have provided better detection accuracy of 99.3% and 99.5%, respectively.

With the ever increasing threat of malware, extensive research effort has been put on applying Deep Learning for malware classification tasks. Graph Neural Networks (GNNs) that process malware as Control Flow Graphs (CFGs) have shown great promise for malware classification. However, these models are viewed as black-boxes, which makes it hard to validate and identify malicious patterns. To that end, we propose CFG-Explainer, a deep learning based model for interpreting GNN-oriented malware classification results. CFGExplainer identifies a subgraph of the malware CFG that contributes most towards classification and provides insight into importance of the nodes (i.e., basic blocks) within it. To the best of our knowledge, CFGExplainer is the first work that explains GNN-based mal-ware classification. We compared CFGExplainer against three explainers, namely GNNExplainer, SubgraphX and PGExplainer, and showed that CFGExplainer is able to identify top equisized subgraphs with higher classification accuracy than the other three models.

With the dramatic increase in malicious software, the sophistication and innovation of malware have increased over the years. In particular, the dynamic analysis based on the deep neural network has shown high accuracy in malware detection. However, most of the existing methods only employ the raw API sequence feature, which cannot accurately reflect the actual behavior of malicious programs in detail. The relationship between API calls is critical for detecting suspicious behavior. Therefore, this paper proposes a malware detection method based on the graph neural network. We first connect the API sequences executed by different processes to build a directed process graph. Then, we apply Bert to encode the API sequences of each process into node embedding, which facilitates the semantic execution information inside the processes. Finally, we employ GCN to mine the deep semantic information based on the directed process graph and node embedding. In addition to presenting the design, we have implemented and evaluated our method on 10,000 malware and 10,000 benign software datasets. The results show that the precision and recall of our detection model reach 97.84% and 97.83%, verifying the effectiveness of our proposed method.

Nowadays, the popularity of intelligent terminals makes malwares more and more serious. Among the many features of application, the call graph can accurately express the behavior of the application. The rapid development of graph neural network in recent years provides a new solution for the malicious analysis of application using call graphs as features. However, there are still problems such as low accuracy. This paper established a large-scale data set containing more than 40,000 samples and selected the class call graph, which was extracted from the application, as the feature and used the graph embedding combined with the deep neural network to detect the malware. The experimental results show that the accuracy of the detection model proposed in this paper is 97.7%; the precision is 96.6%; the recall is 96.8%; the F1-score is 96.4%, which is better than the existing detection model based on Markov chain and graph embedding detection model.

With large advancements in image display technology, recapturing high-quality images from high-fidelity LCD screens becomes much easier. Such recaptured images can be used to hide image tampering traces and fool some intelligent identification systems. In order to prevent such a security loophole, we propose a recaptured image detection approach based on generalized central difference convolution (GCDC) network. Specifically, by using GCDC instead of vanilla convolution, more detailed features can be extracted from both intensity and gradient information from an image. Meanwhile, we concatenate the feature maps from multiple GCDC modules to fuse low-, mid-, and high-level features for higher performance. Extensive experiments on three public recaptured image databases demonstrate the superior of our proposed method when compared with the state-of-the-art approaches.

Frame deletion forensics has been a major area of video forensics in recent years. The detection effect of current deep neural network-based methods outperforms previous traditional detection methods. Recently, researchers have used residual features as input to the network to detect frame deletion and have achieved promising results. We propose an IReF (Improved Residual Feature) by analyzing the effect of residual features on frame deletion traces. IReF preserves the main motion features and edge information by denoising and enhancing the residual features, making it easier for the network to identify the tampered features. And the sparse noise reduction reduces the storage requirement. Experiments show that under the 2D convolutional neural network, the accuracy of IReF compared with residual features is increased by 3.81 %, and the storage space requirement is reduced by 78%. In the 3D convolutional neural network with video clips as feature input, the accuracy of IReF features is increased by 5.63%, and the inference efficiency is increased by 18%.

Artificial Intelligence (AI) technology is developing rapidly, permeating every aspect of human life. Although the integration between AI and communication contributes to the flourishing development of wireless communication, it induces severer security problems. As a supplement to the upper-layer cryptography protocol, physical layer security has become an intriguing technology to ensure the security of wireless communication systems. However, most of the current physical layer security research does not consider the intelligence and mobility of collusive eavesdroppers. In this paper, we consider a MIMO system model with a friendly intelligent jammer against multiple collusive intelligent eavesdroppers, and zero-sum game is exploited to formulate the confrontation of them. The Nash equilibrium is derived by convex optimization and alternative optimization in the free-space scenario of a single user system. We propose a zero-sum game deep learning algorithm (ZGDL) for general situations to solve non-convex game problems. In terms of the effectiveness, simulations are conducted to confirm that the proposed algorithm can obtain the Nash equilibrium.

A malicious insider threat is more vulnerable to an organization. It is necessary to detect the malicious insider because of its huge impact to an organization. The occurrence of a malicious insider threat is less but quite destructive. So, the major focus of this paper is to detect the malicious insider threat in an organization. The traditional insider threat detection algorithm is not suitable for real time insider threat detection. A supervised learning-based anomaly detection technique is used to classify, predict and detect the malicious and non-malicious activity based on highest level of anomaly score. In this paper, a framework is proposed to detect the malicious insider threat using supervised learning-based anomaly detection. It is used to detect the malicious insider threat activity using One-Class Support Vector Machine (OCSVM). The experimental results shows that the proposed framework using OCSVM performs well and detects the malicious insider who obtain huge anomaly score than a normal user.

Traffic in a backbone network has high forwarding rate requirements, and as the network gets larger, traffic increases and forwarding rates decrease. In a Software Defined Network (SDN), the controller can manage a global view of the network and control the forwarding of network traffic. A deterministic network has different forwarding requirements for the traffic of different priority levels. Static traffic load balancing is not flexible enough to meet the needs of users and may lead to the overloading of individual links and even network collapse. In this paper, we propose a new backbone network load balancing architecture - EDQN (Edge Deep Q-learning Network), which implements queue-based gate-shaping algorithms at the edge devices and load balancing of traffic on the backbone links. With the advantages of SDN, the link utilization of the backbone network can be improved, the delay in traffic transmission can be reduced and the throughput of traffic during transmission can be increased.

The new paradigm of industrial development, called Industry 4.0, faces the problems of Cybersecurity, and as it has already manifested itself in Information Systems, focuses on the use of Artificial Intelligence tools. The authors of this article build on their experience with the use of the above mentioned tools to increase the resilience of Information Systems against Cyber threats, approached to the choice of an effective structure of Cyber-protection of Industrial Systems, primarily analyzing the objective differences between them and Information Systems. A number of analyzes show increased resilience of the decentralized architecture in the management of large-scale industrial processes to the centralized management architecture. These considerations provide sufficient grounds for the team of the project to give preference to the decentralized structure with flock behavior for further research and experiments. The challenges are to determine the indicators which serve to assess and compare the impacts on the controlled elements.

An Industrial Control System (ICS) is essential in monitoring and controlling critical infrastructures such as safety and security. Internet of Things (IoT) in ICSs allows cyber-criminals to utilize systems' vulnerabilities towards deploying cyber-attacks. To distinguish risks and keep an eye on malicious activity in networking systems, An Intrusion Detection System (IDS) is essential. IDS shall be used by system admins to identify unwanted accesses by attackers in various industries. It is now a necessary component of each organization's security governance. The main objective of this intended work is to establish a deep learning-depended intrusion detection system that can quickly identify intrusions and other unwanted behaviors that have the potential to interfere with networking systems. The work in this paper uses One Hot encoder for preprocessing and the Auto encoder for feature extraction. On KDD99 CUP, a data - set for network intruding, we categorize the normal and abnormal data applying a Deep Convolutional Neural Network (DCNN), a deep learning-based methodology. The experimental findings demonstrate that, in comparison with SVM linear Kernel model, SVM RBF Kernel model, the suggested deep learning model operates better.

Industrial control systems (ICSs) have become more complex due to their increasing connectivity, heterogeneity and, autonomy. As a result, cyber-threats against such systems have been significantly increased as well. Since a compromised industrial system can easily lead to hazardous safety and security consequences, it is crucial to develop security countermeasures to protect coexisting IT systems and industrial physical processes being involved in modern ICSs. Accordingly, in this study, we propose a deep learning-based semantic anomaly detection framework to model the complex behavior of ICSs. In contrast to the related work assuming only simpler security threats targeting individual controllers in an ICS, we address multi-PLC attacks that are harder to detect as requiring to observe the overall system state alongside single-PLC attacks. Using industrial simulation and emulation frameworks, we create a realistic setup representing both the production and networking aspects of industrial systems and conduct some potential attacks. Our experimental results indicate that our model can detect single-PLC attacks with 95% accuracy and multi-PLC attacks with 80% accuracy and nearly 1% false positive rate.

With the rapid development of artificial intelligence technology, deepfake technology based on deep learning is receiving more and more attention from society or the industry. While enriching people's cultural and entertainment life, in-depth fakes technology has also caused many social problems, especially potential risks to managing network credible identities. With the continuous advancement of deep fakes technology, the security threats and trust crisis caused by it will become more serious. It is urgent to take adequate measures to curb the abuse risk of deep fakes. The article first introduces the principles and characteristics of deep fakes technology and then deeply analyzes its severe challenges to network trusted identity management. Finally, it researches the supervision and technical level and puts forward targeted preventive countermeasures.

Rational and smart decision making by means of strategic interaction and mathematical modelling is the key aspect of Game theory. Security games based on game theory are used extensively in cyberspace for various levels of security. The contemporary security issues can be modelled and analyzed using game theory as a robust mathematical framework. The attackers, defenders and the adversarial as well as defensive interactions can be captured using game theory. The security games equilibrium evaluation can help understand the attackers' strategies and potential threats at a deeper level for efficient defense. Wireless sensor network (WSN) designs are greatly benefitted by game theory. A deep learning adversarial network algorithm is used in combination with game theory enabling energy efficiency, optimal data delivery and security in a WSN. The trade-off between energy resource utilization and security is balanced using this technique.

The success of deep learning based steganography has shifted focus of researchers from traditional steganography approaches to deep learning based steganography. Various deep steganographic models have been developed for improved security, capacity and invisibility. In this work a multi-data deep learning steganography model has been developed using a well known deep learning model called Generative Adversarial Networks (GAN) more specifically using deep convolutional Generative Adversarial Networks (DCGAN). The model is capable of hiding two different messages, meant for two different receivers, inside a single cover image. The proposed model consists of four networks namely Generator, Steganalyzer Extractor1 and Extractor2 network. The Generator hides two secret messages inside one cover image which are extracted using two different extractors. The Steganalyzer network differentiates between the cover and stego images generated by the generator network. The experiment has been carried out on CelebA dataset. Two commonly used distortion metrics Peak signal-to-Noise ratio (PSNR) and Structural Similarity Index Metric (SSIM) are used for measuring the distortion in the stego image The results of experimentation show that the stego images generated have good imperceptibility and high extraction rates.

Generative adversarial networks (GANs) have been increasingly popular among deep learning methods. With many GANs-based models developed since its emergence, among which are conditional generative adversarial networks, progressive growing of generative adversarial networks, Wasserstein generative adversarial networks and so on. These frameworks are currently widely applied in areas such as remote sensing cybersecurity, medical, and architecture. Especially, they have solved problems of cloud removal, semantic segmentation, image-to-image translation and data argumentation in remote sensing. For example, WGANs and ProGANs can be applied in data argumentation, and cGANs can be applied in semantic argumentation and image-to-image translation. This article provides an overview of structures of multiple GANs-based models and what areas they can be applied in remote sensing.

Speech enhancement is often applied for speech-based systems due to the proneness of speech signals to additive background noise. While speech processing-based methods are traditionally used for speech enhancement, with advancements in deep learning technologies, many efforts have been made to implement them for speech enhancement. Using deep learning, the networks learn mapping functions from noisy data to clean ones and then learn to reconstruct the clean speech signals. As a consequence, deep learning methods can reduce what is so-called musical noise that is often found in traditional speech enhancement methods. Currently, one popular deep learning architecture for speech enhancement is generative adversarial networks (GAN). However, the cross-entropy loss that is employed in GAN often causes the training to be unstable. So, in many implementations of GAN, the cross-entropy loss is replaced with the least-square loss. In this paper, to improve the training stability of GAN using cross-entropy loss, we propose to use deep regret analytic generative adversarial networks (Dragan) for speech enhancements. It is based on applying a gradient penalty on cross-entropy loss. We also employ relativistic rules to stabilize the training of GAN. Then, we applied it to the least square and Dragan losses. Our experiments suggest that the proposed method improve the quality of speech better than the least-square loss on several objective quality metrics.

In recent years, generative adversarial networks (GAN) have become a research hotspot in the field of deep learning. Researchers apply them to the field of anomaly detection and are committed to effectively and accurately identifying abnormal images in practical applications. In anomaly detection, traditional supervised learning algorithms have limitations in training with a large number of known labeled samples. Therefore, the anomaly detection model of unsupervised learning GAN is the research object for discussion and research. Firstly, the basic principles of GAN are introduced. Secondly, several typical GAN-based anomaly detection models are sorted out in detail. Then by comparing the similarities and differences of each derivative model, discuss and summarize their respective advantages, limitations and application scenarios. Finally, the problems and challenges faced by GAN in anomaly detection are discussed, and future research directions are prospected.

Imbalanced class distribution can cause information loss and missed/false alarms for deep learning and machine-learning algorithms. The detection performance of traditional intrusion detection systems tend to degenerate due to skewed class distribution caused by the uneven allocation of observations in different kinds of attacks. To combat class imbalance and improve network intrusion detection performance, we adopt the conditional generative adversarial network (CTGAN) that enables the generation of samples of specific classes of interest. CTGAN builds on the generative adversarial networks (GAN) architecture to model tabular data and generate high quality synthetic data by conditionally sampling rows from the generated model. Oversampling using CTGAN adds instances to the minority class such that both data in the majority and the minority class are of equal distribution. The generated security alerts are used for training classifiers that realize critical alert detection. The proposed scheme is evaluated on a real-world dataset collected from security operation center of a large enterprise. The experiment results show that detection accuracy can be substantially improved when CTGAN is adopted to produce a balanced security-alert dataset. We believe the proposed CTGAN-based approach can cast new light on building effective systems for critical alert detection with reduced missed/false alarms.

At present, our English error correction algorithm is slightly general, the error correction ability is also very limited, and its accuracy rate is also low, so it is very necessary to improve. This article will further explore the problem of syntax error correction, and the corresponding algorithm model will also be proposed. Based on deep learning technology to improve the error correction rate of English grammar, put forward the corresponding solution, put forward the Sep2seq-based English grammar error correction system model, and carry out a series of rectifications to improve its efficiency and accuracy. The basic architecture of TensorFLOW is used to implement the model, and the success of the error correction algorithm model is proved, which brings great improvement and progress to the success of error correction.

Human facial emotion recognition pays a variety of applications in society. The basic idea of Facial Emotion Recognition is to map the different facial emotions to a variety of emotional states. Conventional Facial Emotion Recognition consists of two processes: extracting the features and feature selection. Nowadays, in deep learning algorithms, Convolutional Neural Networks are primarily used in Facial Emotion Recognition because of their hidden feature extraction from the images. Usually, the standard Convolutional Neural Network has simple learning algorithms with finite feature extraction layers for extracting information. The drawback of the earlier approach was that they validated only the frontal view of the photos even though the image was obtained from different angles. This research work uses a deep Convolutional Neural Network along with a DenseNet-169 as a backbone network for recognizing facial emotions. The emotion Recognition dataset was used to recognize the emotions with an accuracy of 96%.

Facial emotion recognition helps feed the growth of the future artificial intelligence with the development of emotion recognition, learning, and analysis of different angles of a human face and head pose. The world's recent pandemic gave rise to the rapid installment of facial recognition for fewer applications, while emotion recognition is still within the experimental boundaries. The current challenges encountered with facial emotion recognition (FER) are the difference between background noises. Since today's world shows us that humans soon need robotics in the most significant role of human perception, attention, memory, decision-making, and human-robot interaction (HRI) needs employees. By merging the head pose as a combination towards the FER to boost the robustness in understanding emotions using the convolutional neural networks (CNN). The stochastic gradient descent with a comprehensive model is adopted by applying multi-task learning capable of implicit parallelism, inherent and better global optimizer in finding better network weights. After executing a multi-task learning model using two independent datasets, the experiment with the FER and head pose learning multi-views co-regularization frameworks were subsequently merged with validation accuracy.

Facial is the most dynamic part of the human body that conveys information about emotions. The level of diversity in facial geometry and facial look makes it possible to detect various human expressions. To be able to differentiate among numerous facial expressions of emotion, it is crucial to identify the classes of facial expressions. The methodology used in this article is based on convolutional neural networks (CNN). In this paper Deep Learning CNN is used to examine Alex net architectures. Improvements were achieved by applying the transfer learning approach and modifying the fully connected layer with the Support Vector Machine(SVM) classifier. The system succeeded by achieving satisfactory results on icv-the MEFED dataset. Improved models achieved around 64.29 %of recognition rates for the classification of the selected expressions. The results obtained are acceptable and comparable to the relevant systems in the literature provide ideas a background for further improvements.