Biblio

Machine learning (ML) models are increasingly being used in the development of Malware Detection Systems. Existing research in this area primarily focuses on developing new architectures and feature representation techniques to improve the accuracy of the model. However, recent studies have shown that existing state-of-the art techniques are vulnerable to adversarial machine learning (AML) attacks. Among those, data poisoning attacks have been identified as a top concern for ML practitioners. A recent study on clean-label poisoning attacks in which an adversary intentionally crafts training samples in order for the model to learn a backdoor watermark was shown to degrade the performance of state-of-the-art classifiers. Defenses against such poisoning attacks have been largely under-explored. We investigate a recently proposed clean-label poisoning attack and leverage an ensemble-based Nested Training technique to remove most of the poisoned samples from a poisoned training dataset. Our technique leverages the relatively large sensitivity of poisoned samples to feature noise that disproportionately affects the accuracy of a backdoored model. In particular, we show that for two state-of-the art architectures trained on the EMBER dataset affected by the clean-label attack, the Nested Training approach improves the accuracy of backdoor malware samples from 3.42% to 93.2%. We also show that samples produced by the clean-label attack often successfully evade malware classification even when the classifier is not poisoned during training. However, even in such scenarios, our Nested Training technique can mitigate the effect of such clean-label-based evasion attacks by recovering the model's accuracy of malware detection from 3.57% to 93.2%.

The course of operating system's labs usually fall behind the state of art technology. In this paper, we propose a Software Diversity-Assisted Defense (SDAD) lab based on software diversity, mainly targeting for students majoring in cyber security and computer science. This lab is consisted of multiple modules and covers most of the important concepts and principles in operating systems. Thus, the knowledge learned from the theoretical course will be deepened with the lab. For students majoring in cyber security, they can learn this new software diversity-based defense technology and understand how an exploit works from the attacker's side. The experiment is also quite stretchable, which can fit all level students.

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.

The goal of neural style transfer is to transform images by the deep learning method, such as changing oil paintings into sketch-style images. The Generative Adversarial Network (GAN) has made remarkable achievements in neural style transfer in recent years. At first, this paper introduces three typical neural style transfer methods, including StyleGAN, StarGAN, and Transparent Latent GAN (TL-GAN). Then, we discuss the advantages and disadvantages of these models, including the quality of the feature axis, the scale, and the model's interpretability. In addition, as the core of this paper, we put forward innovative improvements to the above models, including how to fully exploit the advantages of the above three models to derive a better style conversion model.

The industrial revolution 4.0 has become a challenge for various sectors in mastering information technology, one of which is the arts and culture sector. Cultural arts that are quite widely spread and developed in Indonesia are traditional masks. Traditional masks are one of the oldest and most beautiful cultures in Indonesia. However, with the development of the era to the digital world in the era of the industrial revolution 4.0, this beloved culture is fading due to the entry of foreign cultures and technological developments. Many young people who succeed the nation do not understand this cultural art, namely traditional masks. So those cultural arts such as traditional masks can still keep up with the development of digital technology in industry 4.0, we conduct research to use technology to preserve this traditional mask culture. The research uses the ADDIE method starting with Analyze, Design, Develop, Implement, and Evaluate. We took some examples of traditional masks such as Malangan masks, Cirebon masks, and Panji masks from several regions in Indonesia. This research implements marker-based Augmented reality technology and makes a traditional mask book that can be a means of augmented reality.

Nowadays, we have witnessed the early progress on learning the association between voice and face automatically, which brings a new wave of studies to the computer vision community. However, most of the prior arts along this line (a) merely adopt local information to perform modality alignment and (b) ignore the diversity of learning difficulty across different subjects. In this paper, we propose a novel framework to jointly address the above-mentioned issues. Targeting at (a), we propose a two-level modality alignment loss where both global and local information are considered. Compared with the existing methods, we introduce a global loss into the modality alignment process. The global component of the loss is driven by the identity classification. Theoretically, we show that minimizing the loss could maximize the distance between embeddings across different identities while minimizing the distance between embeddings belonging to the same identity, in a global sense (instead of a mini-batch). Targeting at (b), we propose a dynamic reweighting scheme to better explore the hard but valuable identities while filtering out the unlearnable identities. Experiments show that the proposed method outperforms the previous methods in multiple settings, including voice-face matching, verification and retrieval.

Nowadays, ubiquitous healthcare monitoring applications are becoming a necessity. In a pervasive smart healthcare system, the user's location information is always transmitted periodically to healthcare providers to increase the quality of the service provided to the user. However, revealing the user's location will affect the user's privacy. This paper presents a novel cloud-based secure location privacy-preserving mobile healthcare framework with decision-making capabilities. A user's vital signs are sensed possibly through a wearable healthcare device and transmitted to a cloud server for securely storing user's data, processing, and decision making. The proposed framework integrates a number of features such as machine learning (ML) for classifying a user's health state, and crowdsensing for collecting information about a person's privacy preferences for possible locations and applying such information to a user who did not set his privacy preferences. In addition to location privacy preservation methods (LPPM) such as obfuscation, perturbation and encryption to protect the location of the user and provide a secure monitoring framework. The proposed framework detects clear emergency cases and quickly decides about sending a help message to a healthcare provider before sending data to the cloud server. To validate the efficiency of the proposed framework, a prototype is developed and tested. The obtained results from the proposed prototype prove its feasibility and utility. Compared to the state of art, the proposed framework offers an adaptive context-based decision for location sharing privacy and controlling the trade-off between location privacy and service utility.

For real-time applications of arbitrary style transformation, there is a trade-off between the quality of results and the running time of existing algorithms. Hence, it is required to maintain the equilibrium of the quality of generated artwork with the speed of execution. It's complicated for the present arbitrary style-transformation procedures to preserve the structure of content-image while blending with the design and pattern of style-image. This paper presents the implementation of a network using SANET models for generating impressive artworks. It is flexible in the fusion of new style characteristics while sustaining the semantic-structure of the content-image. The identity-loss function helps to minimize the overall loss and conserves the spatial-arrangement of content. The results demonstrate that this method is practically efficient, and therefore it can be employed for real-time fusion and transformation using arbitrary styles.

Since Gatys et al. proved that the convolution neural network (CNN) can be used to generate new images with artistic styles by separating and recombining the styles and contents of images. Neural Style Transfer has attracted wide attention of computer vision researchers. This paper aims to provide an overview of the style transfer application deep learning network development process, and introduces the classical style migration model, on the basis of the research on the migration of style of the deep learning network for collecting and organizing, and put forward related to gathered during the investigation of the problem solution, finally some classical model in the image style to display and compare the results of migration.

Most of the notable artworks of all time are hand drawn by great artists. But, now with the advancement in image processing and huge computation power, very sophisticated synthesised artworks are being produced. Since mid-1990's, computer graphics engineers have come up with algorithms to produce digital paintings, but the results were not visually appealing. Recently, neural networks have been used to do this task and the results seen are like never before. One such algorithm for this purpose is the neural style transfer algorithm, which imparts the pattern from one image to another, producing marvellous pieces of art. This research paper focuses on the roles of various parameters involved in the neural style transfer algorithm. An extensive analysis of how these parameters influence the output, in terms of time, performance and quality of the style transferred image produced is also shown in the paper. A concrete comparison has been drawn on the basis of different time and performance metrics. Finally, optimal values for these discussed parameters have been suggested.

Humans have created many pioneers of art from the beginning of time. There are not many notable achievements by an artificial intelligence to create something visually captivating in the field of art. However, some breakthroughs were made in the past few years by learning the differences between the content and style of an image using convolution neural networks and texture synthesis. But most of the approaches have the limitations on either processing time, choosing a certain style image or altering the weight ratio of style image. Therefore, we are to address these restrictions and provide a system which allows any style image selection with a user defined style weight ratio in minimum time possible.

In today's society, even though the technology is so developed, the coloring of computer images has remained at the manual stage. As a carrier of human culture and art, film has existed in our history for hundred years. With the development of science and technology, movies have developed from the simple black-and-white film era to the current digital age. There is a very complicated process for coloring old movies. Aside from the traditional hand-painting techniques, the most common method is to use post-processing software for coloring movie frames. This kind of operation requires extraordinary skills, patience and aesthetics, which is a great test for the operator. In recent years, the extensive use of machine learning and neural networks has made it possible for computers to intelligently process images. Since 2016, various types of generative adversarial networks models have been proposed to make deep learning shine in the fields of image style transfer, image coloring, and image style change. In this case, the experiment uses the generative adversarial networks principle to process pictures and videos to realize the automatic rendering of old documentary movies.

Nowadays, The incorporation of different function of the network, as well as routing, administration, and security, is basic to the effective operation of a mobile circumstantial network these days, in MANET thought researchers manages the problems of QoS and security severally. Currently, each the aspects of security and QoS influence negatively on the general performance of the network once thought-about in isolation. In fact, it will influence the exceptionally operating of QoS and security algorithms and should influence the important and essential services needed within the MANET. Our paper outlines 2 accomplishments via; the accomplishment of security and accomplishment of quality. The direction towards achieving these accomplishments is to style and implement a protocol to suite answer for policy-based network administration, and methodologies for key administration and causing of IPsec in a very MANET.

The increasing amount of malware variants seen in the wild is causing problems for Antivirus Software vendors, unable to keep up by creating signatures for each. The methods used to develop a signature, static and dynamic analysis, have various limitations. Machine learning has been used by Antivirus vendors to detect malware based on the information gathered from the analysis process. However, adversarial examples can cause machine learning algorithms to miss-classify new data. In this paper we describe a method for malware analysis by converting malware binaries to images and then preparing those images for training within a Generative Adversarial Network. These unsupervised deep neural networks are not susceptible to adversarial examples. The conversion to images from malware binaries should be faster than using dynamic analysis and it would still be possible to link malware families together. Using the Generative Adversarial Network, malware detection could be much more effective and reliable.

In recent years, the big-data approach has become important within various business operations and sales judgment tactics. Contrarily, numerous privacy problems limit the progress of their analysis technologies. To mitigate such problems, this paper proposes several privacy-preserving methods, i.e., anonymization, extreme value record elimination, fully encrypted analysis, and so on. However, privacy-cracking fears still remain that prevent the open use of big-data by other, external organizations. We propose a big-data reconstruction method that does not intrinsically use privacy data. The method uses only the statistical features of big-data, i.e., its attribute histograms and their correlation coefficients. To verify whether valuable information can be extracted using this method, we evaluate the data by using Self Organizing Map (SOM) as one of the big-data analysis tools. The results show that the same pieces of information are extracted from our data and the big-data.

The recently applied General Data Protection Regulation (GDPR) aims to protect all EU citizens from privacy and data breaches in an increasingly data-driven world. Consequently, this deeply affects the factory domain and its human-centric automation paradigm. Especially collaboration of human and machines as well as individual support are enabled and enhanced by processing audio and video data, e.g. by using algorithms which re-identify humans or analyse human behaviour. We introduce most significant impacts of the recent legal regulation change towards the automations domain at a glance. Furthermore, we introduce a representative scenario from production, deduce its legal affections from GDPR resulting in a privacy-aware software architecture. This architecture covers modern virtualization techniques along with authorization and end-to-end encryption to ensure a secure communication between distributes services and databases for distinct purposes.

In this paper, inspired by Gatys's recent work, we propose a novel approach that transforms photos to comics using deep convolutional neural networks (CNNs). While Gatys's method that uses a pre-trained VGG network generally works well for transferring artistic styles such as painting from a style image to a content image, for more minimalist styles such as comics, the method often fails to produce satisfactory results. To address this, we further introduce a dedicated comic style CNN, which is trained for classifying comic images and photos. This new network is effective in capturing various comic styles and thus helps to produce better comic stylization results. Even with a grayscale style image, Gatys's method can still produce colored output, which is not desirable for comics. We develop a modified optimization framework such that a grayscale image is guaranteed to be synthesized. To avoid converging to poor local minima, we further initialize the output image using grayscale version of the content image. Various examples show that our method synthesizes better comic images than the state-of-the-art method.

The term steganography was used to conceal thesecret message into other media file. In this paper, a novel imagesteganography is proposed, based on adaptive neural networkswith recycling the Improved Absolute Moment Block TruncationCoding algorithm, and by employing the enhanced five edgedetection operators with an optimal target of the ANNS. Wepropose a new scheme of an image concealing using hybridadaptive neural networks based on I-AMBTC method by thehelp of two approaches, the relevant edge detection operators andimage compression methods. Despite that, many processes in ourscheme are used, but still the quality of concealed image lookinggood according to the HVS and PVD systems. The final simulationresults are discussed and compared with another related researchworks related to the image steganography system.

Transportation costs for road transport companies may be intensified by rising fuel prices, levies, traffic congestion, etc. Of particular concern to the Mpact group of companies is the long waiting times in the queues at loading and offloading points at three processing mills in the KZN (KwaZulu-Natal) province in South Africa. Following a survey among the drivers who regularly deliver at these sites, recommendations for alleviating the lengthy waiting times are put forward. On the strength of one of these recommendations, namely the innovative use of ICTs, suggestions on how cloud-based technologies may be embraced by the company are explored. In the process, the value added by a cloud-based supply chain, enterprise systems, CRM (Customer Relationship Management) and knowledge management is examined.

Security of secret data has been a major issue of concern from ancient time. Steganography and cryptography are the two techniques which are used to reduce the security threat. Cryptography is an art of converting secret message in other than human readable form. Steganography is an art of hiding the existence of secret message. These techniques are required to protect the data theft over rapidly growing network. To achieve this there is a need of such a system which is very less susceptible to human visual system. In this paper a new technique is going to be introducing for data transmission over an unsecure channel. In this paper secret data is compressed first using LZW algorithm before embedding it behind any cover media. Data is compressed to reduce its size. After compression data encryption is performed to increase the security. Encryption is performed with the help of a key which make it difficult to get the secret message even if the existence of the secret message is reveled. Now the edge of secret message is detected by using canny edge detector and then embedded secret data is stored there with the help of a hash function. Proposed technique is implemented in MATLAB and key strength of this project is its huge data hiding capacity and least distortion in Stego image. This technique is applied over various images and the results show least distortion in altered image.

Preserving the availability and integrity of networked computing systems in the face of fast-spreading intrusions requires advances not only in detection algorithms, but also in automated response techniques. In this paper, we propose a new approach to automated response called the response and recovery engine (RRE). Our engine employs a game-theoretic response strategy against adversaries modeled as opponents in a two-player Stackelberg stochastic game. The RRE applies attack-response trees (ART) to analyze undesired system-level security events within host computers and their countermeasures using Boolean logic to combine lower level attack consequences. In addition, the RRE accounts for uncertainties in intrusion detection alert notifications. The RRE then chooses optimal response actions by solving a partially observable competitive Markov decision process that is automatically derived from attack-response trees. To support network-level multiobjective response selection and consider possibly conflicting network security properties, we employ fuzzy logic theory to calculate the network-level security metric values, i.e., security levels of the system's current and potentially future states in each stage of the game. In particular, inputs to the network-level game-theoretic response selection engine, are first fed into the fuzzy system that is in charge of a nonlinear inference and quantitative ranking of the possible actions using its previously defined fuzzy rule set. Consequently, the optimal network-level response actions are chosen through a game-theoretic optimization process. Experimental results show that the RRE, using Snort's alerts, can protect large networks for which attack-response trees have more than 500 nodes.