Biblio

Transferring the style of an image is a fundamental problem in computer vision. Which extracts the features of a context image and a style image, then fixes them to produce a new image with features of the both two input images. In this paper, we introduce an artificial system to separate and recombine the content and style of arbitrary images, providing a neural algorithm for the creation of artistic images. We use a pre-trained deep convolutional neural network VGG19 to extract the feature map of the input style image and context image. Then we define a loss function that captures the difference between the output image and the two input images. We use the gradient descent algorithm to update the output image to minimize the loss function. Experiment results show the feasibility of the method.

In painting, humans can draw an interrelation between the style and the content of a given image in order to enhance visual experiences. Deep neural networks like convolutional neural networks are being used to draw a satisfying conclusion of this problem of neural style transfer due to their exceptional results in the key areas of visual perceptions such as object detection and face recognition.In this study, along with style transfer on whole image it is also outlined how transfer of style can be performed only on the specific parts of the content image which is accomplished by using masks. The style is transferred in a way that there is a least amount of loss to the content image i.e., semantics of the image is preserved.

The Moving Picture Experts Group's Compact Descriptors for Visual Search (MPEG's CDVS) intends to standardize technologies in order to enable an interoperable, efficient, and cross-platform solution for internet-scale visual search applications and services. Among the key technologies within CDVS, we recall the format of visual descriptors, the descriptor extraction process, and the algorithms for indexing and matching. Unfortunately, these steps require precision and computation accuracy. Moreover, they are very time-consuming, as they need running times in the order of seconds when implemented on the central processing unit (CPU) of modern mobile devices. In this paper, to reduce computation times and maintain precision and accuracy, we re-design, for many-cores embedded graphical processor units (GPUs), all main local descriptor extraction pipeline phases of the MPEG's CDVS standard. To reach this goal, we introduce new techniques to adapt the standard algorithm to parallel processing. Furthermore, to reduce memory accesses and efficiently distribute the kernel workload, we use new approaches to store and retrieve CDVS information on proper GPU data structures. We present a complete experimental analysis on a large and standard test set. Our experiments show that our GPU-based approach is remarkably faster than the CPU-based reference implementation of the standard, and it maintains a comparable precision in terms of true and false positive rates.

Digital-Twins simulate physical world objects by creating 'as-is' virtual images in a cyberspace. In order to create a well synchronized digital-twin simulator in manufacturing, information and activities of a physical machine need to be virtualized. Many existing digital-twins stream read-only data of machine sensors and do not incorporate operations of manufacturing machines through Internet. In this paper, a new method of virtualization is proposed to integrate machining data and operations into the digital-twins using Internet scale machine tool communication method. A fully functional digital-twin is implemented in CPMC testbed using MTComm and several manufacturing application scenarios are developed to evaluate the proposed method and system. Performance analysis shows that it is capable of providing data-driven visual monitoring of a manufacturing process and performing manufacturing operations through digital twins over the Internet. Results of the experiments also shows that the MTComm based digital twins have an excellent efficiency.

FastChain is a simulator built in NS-3 which simulates the networked battlefield scenario with military applications, connecting tankers, soldiers and drones to form Internet-of-Battlefield-Things (IoBT). Computing, storage and communication resources in IoBT are limited during certain situations in IoBT. Under these circumstances, these resources should be carefully combined to handle the task to accomplish the mission. FastChain simulator uses Sharding approach to provide an efficient solution to combine resources of IoBT devices by identifying the correct and the best set of IoBT devices for a given scenario. Then, the set of IoBT devices for a given scenario collaborate together for sharding enabled Blockchain technology. Interested researchers, policy makers and developers can download and use the FastChain simulator to design, develop and evaluate blockchain enabled IoBT scenarios that helps make robust and trustworthy informed decisions in mission-critical IoBT environment.

Several cloud providers have started to offer specific data management services by responding to the new trend called the Internet of Things (IoT). In recent years, we have already seen that cloud computing has managed to serve IoT needs for data retrieval, processing and visualization transparent for the user side. IoT-Cloud systems for smart cities and smart regions can be very complex, therefore their design and analysis should be supported by means of simulation. Nevertheless, the models used in simulation environments should be as close as to the real world utilization to provide reliable results. To facilitate such simulations, in earlier works we proposed an IoT trace archiving service called SUMMON that can be used to gather real world datasets, and to reuse them for simulation experiments. In this paper we provide an extension to SUMMON with an automated web crawling service that gathers IoT and sensor data from publicly available websites. We introduce the architecture and operation of this approach, and exemplify it utilization with three use cases. The provided archiving solution can be used by simulators to perform realistic evaluations.

Training the future cybersecurity workforce to respond to emerging threats requires introduction of novel educational interventions into the cybersecurity curriculum. To be effective, these interventions have to incorporate trending knowledge from cybersecurity and other related domains while allowing for experiential learning through hands-on experimentation. To date, the traditional interdisciplinary approach for cybersecurity training has infused political science, law, economics or linguistics knowledge into the cybersecurity curriculum, allowing for limited experimentation. Cybersecurity students were left with little opportunity to acquire knowledge, skills, and abilities in domains outside of these. Also, students in outside majors had no options to get into cybersecurity. With this in mind, we developed an interdisciplinary course for experiential learning in the fields of cybersecurity and interaction design. The inaugural course teaches students from cybersecurity, user interaction design, and visual design the principles of designing for secure use - or secure design - and allows them to apply them for prototyping of Internet-of-Things (IoT) products for smart homes. This paper elaborates on the concepts of secure design and how our approach enhances the training of the future cybersecurity workforce.

Malicious software, known as malware, has become urgently serious threat for computer security, so automatic mal-ware classification techniques have received increasing attention. In recent years, deep learning (DL) techniques for computer vision have been successfully applied for malware classification by visualizing malware files and then using DL to classify visualized images. Although DL-based classification systems have been proven to be much more accurate than conventional ones, these systems have been shown to be vulnerable to adversarial attacks. However, there has been little research to consider the danger of adversarial attacks to visualized image-based malware classification systems. This paper proposes an adversarial attack method based on the gradient to attack image-based malware classification systems by introducing perturbations on resource section of PE files. The experimental results on the Malimg dataset show that by a small interference, the proposed method can achieve success attack rate when challenging convolutional neural network malware classifiers.

Classifying malware programs is a research area attracting great interest for Anti-Malware industry. In this research, we propose a system that visualizes malware programs as images and distinguishes those using Convolutional Neural Networks (CNNs). We study the performance of several well-established CNN based algorithms such as AlexNet, ResNet and VGG16 using transfer learning approaches. We also propose a computationally efficient CNN-based architecture for classification of malware programs. In addition, we study the performance of these CNNs as feature extractors by using Support Vector Machine (SVM) and K-nearest Neighbors (kNN) for classification purposes. We also propose fusion methods to boost the performance further. We make use of the publicly available database provided by Microsoft Malware Classification Challenge (BIG 2015) for this study. Our overall performance is 99.4% for a set of 2174 test samples comprising 9 different classes thereby setting a new benchmark.

The last decade has witnessed an increase in online human interactions, covering all aspects of personal and professional activities. Identification of people based on their behavior rather than physical traits is a growing industry, spanning diverse spheres such as online education, e-commerce and cyber security. One prominent behavior is the expression of opinions, commonly as a reaction to images posted online. Visual aesthetic is a soft, behavioral biometric that refers to a person's sense of fondness to a certain image. Identifying individuals using their visual aesthetics as discriminatory features is an emerging domain of research. This paper introduces a new method for aesthetic feature dimensionality reduction using gene expression programming. The advantage of this method is that the resulting system is capable of using a tree-based genetic approach for feature recombination. Reducing feature dimensionality improves classifier accuracy, reduces computation runtime, and minimizes required storage. The results obtained on a dataset of 200 Flickr users evaluating 40000 images demonstrates a 94% accuracy of identity recognition based solely on users' aesthetic preferences. This outperforms the best-known method by 13.5%.

With rapid growth of network size and complexity, network defenders are facing more challenges in protecting networked computers and other devices from acute attacks. Traffic visualization is an essential element in an anomaly detection system for visual observations and detection of distributed DoS attacks. This paper presents an interactive visualization system called TVis, proposed to detect both low-rate and highrate DDoS attacks using Heron's triangle-area mapping. TVis allows network defenders to identify and investigate anomalies in internal and external network traffic at both online and offline modes. We model the network traffic as an undirected graph and compute triangle-area map based on incidences at each vertex for each 5 seconds time window. The system triggers an alarm iff the system finds an area of the mapped triangle beyond the dynamic threshold. TVis performs well for both low-rate and high-rate DDoS detection in comparison to its competitors.

The world is fundamentally compositional, so it is natural to think of visual recognition as the recognition of basic visually primitives that are composed according to well-defined rules. This strategy allows us to recognize unseen complex concepts from simple visual primitives. However, the current trend in visual recognition follows a data greedy approach where huge amounts of data are required to learn models for any desired visual concept. In this paper, we build on the compositionality principle and develop an "algebra" to compose classifiers for complex visual concepts. To this end, we learn neural network modules to perform boolean algebra operations on simple visual classifiers. Since these modules form a complete functional set, a classifier for any complex visual concept defined as a boolean expression of primitives can be obtained by recursively applying the learned modules, even if we do not have a single training sample. As our experiments show, using such a framework, we can compose classifiers for complex visual concepts outperforming standard baselines on two well-known visual recognition benchmarks. Finally, we present a qualitative analysis of our method and its properties.

Various perceptual domains have underlying compositional semantics that are rarely captured in current models. We suspect this is because directly learning the compositional structure has evaded these models. Yet, the compositional structure of a given domain can be grounded in a separate domain thereby simplifying its learning. To that end, we propose a new approach to modeling bimodal perceptual domains that explicitly relates distinct projections across each modality and then jointly learns a bimodal sparse representation. The resulting model enables compositionality across these distinct projections and hence can generalize to unobserved percepts spanned by this compositional basis. For example, our model can be trained on red triangles and blue squares; yet, implicitly will also have learned red squares and blue triangles. The structure of the projections and hence the compositional basis is learned automatically; no assumption is made on the ordering of the compositional elements in either modality. Although our modeling paradigm is general, we explicitly focus on a tabletop building-blocks setting. To test our model, we have acquired a new bimodal dataset comprising images and spoken utterances of colored shapes (blocks) in the tabletop setting. Our experiments demonstrate the benefits of explicitly leveraging compositionality in both quantitative and human evaluation studies.

We investigate a deep learning model for action recognition that simultaneously extracts spatio-temporal information from a raw RGB input data. The proposed multiple spatio-temporal scales recurrent neural network (MSTRNN) model is derived by combining multiple timescale recurrent dynamics with a conventional convolutional neural network model. The architecture of the proposed model imposes both spatial and temporal constraints simultaneously on its neural activities. The constraints vary, with multiple scales in different layers. As suggested by the principle of upward and downward causation, it is assumed that the network can develop a functional hierarchy using its constraints during training. To evaluate and observe the characteristics of the proposed model, we use three human action datasets consisting of different primitive actions and different compositionality levels. The performance capabilities of the MSTRNN model on these datasets are compared with those of other representative deep learning models used in the field. The results show that the MSTRNN outperforms baseline models while using fewer parameters. The characteristics of the proposed model are observed by analyzing its internal representation properties. The analysis clarifies how the spatio-temporal constraints of the MSTRNN model aid in how it extracts critical spatio-temporal information relevant to its given tasks.

A cooperative network defense is one approach to fend off large-scale Distributed Denial-of-Service (DDoS) attacks. In this regard, the Blockchain Signaling System (BloSS) is a multi-domain, blockchain-based, cooperative DDoS defense system, where each Autonomous System (AS) is taking part in the defense alliance. Each AS can exchange attack information about ongoing attacks via the Ethereum blockchain. However, the currently operational implementation of BloSS is not interactive or visualized, but the DDoS mitigation is automated. In realworld defense systems, a human cybersecurity analyst decides whether a DDoS threat should be mitigated or not. Thus, this work presents the design of a security management dashboard for BloSS, designed for interactive use by cyber security analysts.

The presented method of encoding and steganographic embedding of a series of bits for the hidden message was first developed by modifying the digital platform (bases) of the elements of the image container. Unlike other methods, steganographic coding and embedding is accomplished by changing the elements of the image fragment, followed by the formation of code structures for the established structure of the digital representation of the structural elements of the image media image. The method of estimating quantitative indicators of embedded critical data is presented. The number of bits of the container for the developed method of steganographic coding and embedding of critical information is estimated. The efficiency of the presented method is evaluated and the comparative analysis of the value of the embedded digital data in relation to the method of weight coefficients of the discrete cosine transformation matrix, as well as the comparative analysis of the developed method of steganographic coding, compared with the Koch and Zhao methods to determine the embedded data resistance against attacks of various types. It is determined that for different values of the quantization coefficient, the most critical are the built-in containers of critical information, which are built by changing the part of the digital video data platform depending on the size of the digital platform and the number of bits of the built-in container.

The accuracy of the image classification by the convolutional neural network is exceeding the ability of human being and contributes to various fields. However, the improvement of the image recognition technology gives a great blow to security system with an image such as CAPTCHA. In particular, since the character string CAPTCHA has already added distortion and noise in order not to be read by the computer, it becomes a problem that the human readability is lowered. Adversarial examples is a technique to produce an image letting an image classification by the machine learning be wrong intentionally. The best feature of this technique is that when human beings compare the original image with the adversarial examples, they cannot understand the difference on appearance. However, Adversarial examples that is created with conventional FGSM cannot completely misclassify strong nonlinear networks like CNN. Osadchy et al. have researched to apply this adversarial examples to CAPTCHA and attempted to let CNN misclassify them. However, they could not let CNN misclassify character images. In this research, we propose a method to apply FGSM to the character string CAPTCHAs and to let CNN misclassified them.

To prevent unauthorized access to adversaries, strong authentication scheme is a vital security requirement in client-server inter-networking systems. These schemes must verify the legitimacy of such users in real-time environments and establish a dynamic session key fur subsequent communication. Of late, T. H. Chen and J. C. Huang proposed a two-factor authentication framework claiming that the scheme is secure against most of the existing attacks. However we have shown that Chen and Huang scheme have many critical weaknesses in real-time environments. The scheme is prone to man in the middle attack and information leakage attack. Furthermore, the scheme does not provide two essential security services such user anonymity and session key establishment. In this paper, we present an enhanced user participating authenticating scheme which overcomes all the weaknesses of Chen et al.'s scheme and provide most of the essential security features.

Bitcoin [1] as a popular digital currency has been a target of theft and other illegal activities. Key to the forensic investigation is to identify bitcoin addresses involved in bitcoin transfers. This paper presents a framework, FABT, for forensic analysis of bitcoin transactions by identifying suspicious bitcoin addresses. It formalizes the clues of a given case as transaction patterns defined over a comprehensive set of features. FABT converts the bitcoin transaction data into a formal model, called Bitcoin Transaction Net (BTN). The traverse of all bitcoin transactions in the order of their occurrences is captured by the firing sequence of all transitions in the BTN. We have applied FABT to identify suspicious addresses in the Mt.Gox case. A subgroup of the suspicious addresses has been found to share many characteristics about the received/transferred amount, number of transactions, and time intervals.

Most augmented reality applications connect virtual information to anchors, i.e. physical places or objects, by using spatial overlays or proximity. However, for industrial use cases this is not always feasible because specific parts must remain fully visible in order to meet work or security requirements. In these situations virtual information must be displayed at alternative positions while connections to anchors must still be clearly recognizable. In our previous research we were the first to show that for simple scenes connection lines are most suitable for this. To extend these results to more complex environments, we conducted an experiment on the effects of visual interruptions in connection lines and incorrect occlusion. Completion time and subjective mental effort for search tasks were used as measures. Our findings confirm that also in 3D scenes with partial occlusion connection lines are preferable to connect virtual information with anchors if an assignment via overlay or close proximity is not feasible. The results further imply that neither incorrectly used depth cues nor missing parts of connection lines make a significant difference concerning completion time or subjective mental effort. For designers of industrial augmented reality applications this means that they can choose either visualization based on their needs.

Model explanations based on pure observational data cannot compute the effects of features reliably, due to their inability to estimate how each factor alteration could affect the rest. We argue that explanations should be based on the causal model of the data and the derived intervened causal models, that represent the data distribution subject to interventions. With these models, we can compute counterfactuals, new samples that will inform us how the model reacts to feature changes on our input. We propose a novel explanation methodology based on Causal Counterfactuals and identify the limitations of current Image Generative Models in their application to counterfactual creation.

Today's software is full of security vulnerabilities that invite attack. Attackers are especially drawn to software systems containing sensitive data. For such systems, this paper presents a modeling approach especially suited for Serum or other forms of agile development to identify and reduce the attack surface. The latter arises due to the locations containing sensitive data within the software system that are reachable by attackers. The approach reduces the attack surface by changing the design so that the number of such locations is reduced. The approach performs these changes on a visual model of the software system. The changes are then considered for application to the actual system to improve its security.

Trademarks are recognizable images and/or words used to distinguish various products or services. They become associated with the reputation, innovation, quality, and warranty of the products. Countries around the world have offices for industrial/intellectual property (IP) registration. A new trademark image in application for registration should be distinct from all the registered trademarks. Due to the volume of trademark registration applications and the size of the databases containing existing trademarks, it is impossible for humans to make all the comparisons visually. Therefore, technological tools are essential for this task. In this work we use a pre-trained, publicly available Convolutional Neural Network (CNN) VGG19 that was trained on the ImageNet database. We adapted the VGG19 for the trademark image retrieval (TIR) task by fine tuning the network using two different databases. The VGG19v was trained with a database organized with trademark images using visual similarities, and the VGG19c was trained using trademarks organized by using conceptual similarities. The database for the VGG19v was built using trademarks downloaded from the WEB, and organized by visual similarity according to experts from the IP office. The database for the VGG19c was built using trademark images from the United States Patent and Trademarks Office and organized according to the Vienna conceptual protocol. The TIR was assessed using the normalized average rank for a test set from the METU database that has 922,926 trademark images. We computed the normalized average ranks for VGG19v, VGG19c, and for a combination of both networks. Our method achieved significantly better results on the METU database than those published previously.

With the rapid development of the Internet, the dark network has also been widely used in the Internet [1]. Due to the anonymity of the dark network, many illegal elements have committed illegal crimes on the dark. It is difficult for law enforcement officials to track the identity of these cyber criminals using traditional network survey techniques based on IP addresses [2]. The threat information is mainly from the dark web forum and the dark web market. In this paper, we introduce the current mainstream dark network communication system TOR and develop a visual dark web forum post association analysis system to graphically display the relationship between various forum messages and posters, and help law enforcement officers to explore deep levels. Clues to analyze crimes in the dark network.

In the past few years, visual information collection and transmission is increased significantly for various applications. Smart vehicles, service robotic platforms and surveillance cameras for the smart city applications are collecting a large amount of visual data. The preservation of the privacy of people presented in this data is an important factor in storage, processing, sharing and transmission of visual data across the Internet of Robotic Things (IoRT). In this paper, a novel anonymisation method for information security and privacy preservation in visual data in sharing layer of the Web of Robotic Things (WoRT) is proposed. The proposed framework uses deep neural network based semantic segmentation to preserve the privacy in video data base of the access level of the applications and users. The data is anonymised to the applications with lower level access but the applications with higher legal access level can analyze and annotated the complete data. The experimental results show that the proposed method while giving the required access to the authorities for legal applications of smart city surveillance, is capable of preserving the privacy of the people presented in the data.