Biblio

Producing an editable model texture could be a challenging problem if the model is scanned from real world or generated by multi-view reconstruction algorithm. To solve this problem, we present a novel re-topology and UV remapping method based on neural network, which transforms arbitrary models with textured coordinates to a semi-regular meshes, and keeps models texture and removes the influence of lighting information. The main innovation of this paper is to use a neural network to find the appropriate location of the starting and ending points for models in the UV maps. Then each fragmented mesh is projected to the 2D planar domain. After calculating and optimizing the orientation field, a semi-regular mesh for each patch is then generated. Those patches can be projected back to three-dimension space and be spliced to a complete mesh. Experiments show that our method can achieve satisfactory performance.

With technological advancements and increment in content based advertisement, the use of Short Message Service (SMS) on phones has increased to such a significant level that devices are sometimes flooded with a number of spam SMS. These spam messages can lead to loss of private data as well. There are many content-based machine learning techniques which have proven to be effective in filtering spam emails. Modern day researchers have used some stylistic features of text messages to classify them to be ham or spam. SMS spam detection can be greatly influenced by the presence of known words, phrases, abbreviations and idioms. This paper aims to compare different classifying techniques on different datasets collected from previous research works, and evaluate them on the basis of their accuracies, precision, recall and CAP Curve. The comparison has been performed between traditional machine learning techniques and deep learning methods.

BP algorithm used by autoencoder classification algorithm. But the BP algorithm is not only complicated and inefficient, but sometimes falls into local optimum. This makes autoencoder classification algorithm are not very good. So in this paper we combie Quantum Particle Swarm Optimization (QPSO) and autoencoder classification algorithm. QPSO used to optimize the weight of autoencoder neural network and the parameter of softmax. This method has been tested on some database, and the experimental result shows that this method has got good results.

In the field of Cyber Security there has been a transition from the stage of Cyber Criminality to the stage of Cyber War over the last few years. According to the new challenges, the expert community has two main approaches: to adopt the philosophy and methods of Military Intelligence, and to use Artificial Intelligence methods for counteraction of Cyber Attacks. \cyrchar\CYRThis paper describes some of the results obtained at Technical University of Sofia in the implementation of project related to the application of intelligent methods for increasing the security in computer networks. The analysis of the feasibility of various Artificial Intelligence methods has shown that a method that is equally effective for all stages of the Cyber Intelligence cannot be identified. While for Tactical Cyber Threats Intelligence has been selected and experimented a Multi-Agent System, the Recurrent Neural Networks are offered for the needs of Operational Cyber Threats Intelligence.

Machine learning (ML) models are often trained using private datasets that are very expensive to collect, or highly sensitive, using large amounts of computing power. The models are commonly exposed either through online APIs, or used in hardware devices deployed in the field or given to the end users. This provides an incentive for adversaries to steal these ML models as a proxy for gathering datasets. While API-based model exfiltration has been studied before, the theft and protection of machine learning models on hardware devices have not been explored as of now. In this work, we examine this important aspect of the design and deployment of ML models. We illustrate how an attacker may acquire either the model or the model architecture through memory probing, side-channels, or crafted input attacks, and propose (1) power-efficient obfuscation as an alternative to encryption, and (2) timing side-channel countermeasures.

This paper 1 addresses a problem of vulnerability detection in software represented as assembly code. An extended approach to the vulnerability detection problem is proposed. This work concentrates on improvement of neural network-based approach described in previous works of authors. The authors propose to include the morphology of instructions in vector representations. The bidirectional recurrent neural network is used with access to the execution traces of the program. This has significantly improved the vulnerability detecting accuracy.

Neural networks are vulnerable to adversarial examples, which poses a threat to their application in security sensitive systems. We propose high-level representation guided denoiser (HGD) as a defense for image classification. Standard denoiser suffers from the error amplification effect, in which small residual adversarial noise is progressively amplified and leads to wrong classifications. HGD overcomes this problem by using a loss function defined as the difference between the target model's outputs activated by the clean image and denoised image. Compared with ensemble adversarial training which is the state-of-the-art defending method on large images, HGD has three advantages. First, with HGD as a defense, the target model is more robust to either white-box or black-box adversarial attacks. Second, HGD can be trained on a small subset of the images and generalizes well to other images and unseen classes. Third, HGD can be transferred to defend models other than the one guiding it. In NIPS competition on defense against adversarial attacks, our HGD solution won the first place and outperformed other models by a large margin.1

Automatic speaker verification systems are increasingly used as the primary means to authenticate costumers. Recently, it has been proposed to train speaker verification systems using end-to-end deep neural models. In this paper, we show that such systems are vulnerable to adversarial example attacks. Adversarial examples are generated by adding a peculiar noise to original speaker examples, in such a way that they are almost indistinguishable, by a human listener. Yet, the generated waveforms, which sound as speaker A can be used to fool such a system by claiming as if the waveforms were uttered by speaker B. We present white-box attacks on a deep end-to-end network that was either trained on YOHO or NTIMIT. We also present two black-box attacks. In the first one, we generate adversarial examples with a system trained on NTIMIT and perform the attack on a system that trained on YOHO. In the second one, we generate the adversarial examples with a system trained using Mel-spectrum features and perform the attack on a system trained using MFCCs. Our results show that one can significantly decrease the accuracy of a target system even when the adversarial examples are generated with different system potentially using different features.

We construct targeted audio adversarial examples on automatic speech recognition. Given any audio waveform, we can produce another that is over 99.9% similar, but transcribes as any phrase we choose (recognizing up to 50 characters per second of audio). We apply our white-box iterative optimization-based attack to Mozilla's implementation DeepSpeech end-to-end, and show it has a 100% success rate. The feasibility of this attack introduce a new domain to study adversarial examples.

Microsoft's PowerShell is a command-line shell and scripting language that is installed by default on Windows machines. Based on Microsoft's .NET framework, it includes an interface that allows programmers to access operating system services. While PowerShell can be configured by administrators for restricting access and reducing vulnerabilities, these restrictions can be bypassed. Moreover, PowerShell commands can be easily generated dynamically, executed from memory, encoded and obfuscated, thus making the logging and forensic analysis of code executed by PowerShell challenging. For all these reasons, PowerShell is increasingly used by cybercriminals as part of their attacks' tool chain, mainly for downloading malicious contents and for lateral movement. Indeed, a recent comprehensive technical report by Symantec dedicated to PowerShell's abuse by cybercrimials [52] reported on a sharp increase in the number of malicious PowerShell samples they received and in the number of penetration tools and frameworks that use PowerShell. This highlights the urgent need of developing effective methods for detecting malicious PowerShell commands. In this work, we address this challenge by implementing several novel detectors of malicious PowerShell commands and evaluating their performance. We implemented both "traditional" natural language processing (NLP) based detectors and detectors based on character-level convolutional neural networks (CNNs). Detectors' performance was evaluated using a large real-world dataset. Our evaluation results show that, although our detectors (and especially the traditional NLP-based ones) individually yield high performance, an ensemble detector that combines an NLP-based classifier with a CNN-based classifier provides the best performance, since the latter classifier is able to detect malicious commands that succeed in evading the former. Our analysis of these evasive commands reveals that some obfuscation patterns automatically detected by the CNN classifier are intrinsically difficult to detect using the NLP techniques we applied. Our detectors provide high recall values while maintaining a very low false positive rate, making us cautiously optimistic that they can be of practical value.

To add more functionality and enhance usability of web applications, JavaScript (JS) is frequently used. Even with many advantages and usefulness of JS, an annoying fact is that many recent cyberattacks such as drive-by-download attacks exploit vulnerability of JS codes. In general, malicious JS codes are not easy to detect, because they sneakily exploit vulnerabilities of browsers and plugin software, and attack visitors of a web site unknowingly. To protect users from such threads, the development of an accurate detection system for malicious JS is soliciting. Conventional approaches often employ signature and heuristic-based methods, which are prone to suffer from zero-day attacks, i.e., causing many false negatives and/or false positives. For this problem, this paper adopts a machine-learning approach to feature learning called Doc2Vec, which is a neural network model that can learn context information of texts. The extracted features are given to a classifier model (e.g., SVM and neural networks) and it judges the maliciousness of a JS code. In the performance evaluation, we use the D3M Dataset (Drive-by-Download Data by Marionette) for malicious JS codes and JSUPACK for benign ones for both training and test purposes. We then compare the performance to other feature learning methods. Our experimental results show that the proposed Doc2Vec features provide better accuracy and fast classification in malicious JS code detection compared to conventional approaches.

Gatys et al. recently introduced a neural algorithm that renders a content image in the style of another image, achieving so-called style transfer. However, their framework requires a slow iterative optimization process, which limits its practical application. Fast approximations with feed-forward neural networks have been proposed to speed up neural style transfer. Unfortunately, the speed improvement comes at a cost: the network is usually tied to a fixed set of styles and cannot adapt to arbitrary new styles. In this paper, we present a simple yet effective approach that for the first time enables arbitrary style transfer in real-time. At the heart of our method is a novel adaptive instance normalization (AdaIN) layer that aligns the mean and variance of the content features with those of the style features. Our method achieves speed comparable to the fastest existing approach, without the restriction to a pre-defined set of styles. In addition, our approach allows flexible user controls such as content-style trade-off, style interpolation, color & spatial controls, all using a single feed-forward neural network.

``Style transfer'' among images has recently emerged as a very active research topic, fuelled by the power of convolution neural networks (CNNs), and has become fast a very popular technology in social media. This paper investigates the analogous problem in the audio domain: How to transfer the style of a reference audio signal to a target audio content? We propose a flexible framework for the task, which uses a sound texture model to extract statistics characterizing the reference audio style, followed by an optimization-based audio texture synthesis to modify the target content. In contrast to mainstream optimization-based visual transfer method, the proposed process is initialized by the target content instead of random noise and the optimized loss is only about texture, not structure. These differences proved key for audio style transfer in our experiments. In order to extract features of interest, we investigate different architectures, whether pre-trained on other tasks, as done in image style transfer, or engineered based on the human auditory system. Experimental results on different types of audio signal confirm the potential of the proposed approach.

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.

We propose a method for transferring an arbitrary style to only a specific object in an image. Style transfer is the process of combining the content of an image and the style of another image into a new image. Our results show that the proposed method can realize style transfer to specific object.

The paper presents a fully automatic end-to-end trainable system to colorize grayscale images. Colorization is a highly under-constrained problem. In order to produce realistic outputs, the proposed approach takes advantage of the recent advances in deep learning and generative networks. To achieve plausible colorization, the paper investigates conditional Wasserstein Generative Adversarial Networks (WGAN) [3] as a solution to this problem. Additionally, a loss function consisting of two classification loss components apart from the adversarial loss learned by the WGAN is proposed. The first classification loss provides a measure of how much the predicted colored images differ from ground truth. The second classification loss component makes use of ground truth semantic classification labels in order to learn meaningful intermediate features. Finally, WGAN training procedure pushes the predictions to the manifold of natural images. The system is validated using a user study and a semantic interpretability test and achieves results comparable to [1] on Imagenet dataset [10].

In this paper, based on the Hamiltonian, an alternative interpretation about the iterative adaptive dynamic programming (ADP) approach from the perspective of optimization is developed for discrete time nonlinear dynamic systems. The role of the Hamiltonian in iterative ADP is explained. The resulting Hamiltonian driven ADP is able to evaluate the performance with respect to arbitrary admissible policies, compare two different admissible policies and further improve the given admissible policy. The convergence of the Hamiltonian ADP to the optimal policy is proven. Implementation of the Hamiltonian-driven ADP by neural networks is discussed based on the assumption that each iterative policy and value function can be updated exactly. Finally, a simulation is conducted to verify the effectiveness of the presented Hamiltonian-driven ADP.

Deep Neural Network (DNN) has recently become the “de facto” technique to drive the artificial intelligence (AI) industry. However, there also emerges many security issues as the DNN based intelligent systems are being increasingly prevalent. Existing DNN security studies, such as adversarial attacks and poisoning attacks, are usually narrowly conducted at the software algorithm level, with the misclassification as their primary goal. The more realistic system-level attacks introduced by the emerging intelligent service supply chain, e.g. the third-party cloud based machine learning as a service (MLaaS) along with the portable DNN computing engine, have never been discussed. In this work, we propose a low-cost modular methodology-Stealth Infection on Neural Network, namely “SIN2”, to demonstrate the novel and practical intelligent supply chain triggered neural Trojan attacks. Our “SIN2” well leverages the attacking opportunities built upon the static neural network model and the underlying dynamic runtime system of neural computing framework through a bunch of neural Trojaning techniques. We implement a variety of neural Trojan attacks in Linux sandbox by following proposed “SIN2”. Experimental results show that our modular design can rapidly produce and trigger various Trojan attacks that can easily evade the existing defenses.

Neural networks (NNs) are currently a very popular topic in machine learning for both research and practice. GPUs are the dominant computing platform for research efforts and are also gaining popularity as a deployment platform for applications such as autonomous vehicles. As a result, GPU vendors such as NVIDIA have spent enormous effort to write special-purpose NN libraries. On other hardware targets, especially mobile GPUs, such vendor libraries are not generally available. Thus, the development of portable, open, high-performance, energy-efficient GPU code for NN operations would enable broader deployment of NN-based algorithms. A root problem is that high efficiency GPU programming suffers from high complexity, low productivity, and low portability. To address this, this work presents a framework to enable productive, high-efficiency GPU programming for NN computations across hardware platforms and programming models. In particular, the framework provides specific support for metaprogramming and autotuning of operations over ND-Arrays. To show the correctness and value of our framework and approach, we implement a selection of NN operations, covering the core operations needed for deploying three common image-processing neural networks. We target three different hardware platforms: NVIDIA, AMD, and Qualcomm GPUs. On NVIDIA GPUs, we show both portability between OpenCL and CUDA as well competitive performance compared to the vendor library. On Qualcomm GPUs, we show that our framework enables productive development of target-specific optimizations, and achieves reasonable absolute performance. Finally, On AMD GPUs, we show initial results that indicate our framework can yield reasonable performance on a new platform with minimal effort.

This work targets the automated minimum-energy optimization of Quantized Neural Networks (QNNs) - networks using low precision weights and activations. These networks are trained from scratch at an arbitrary fixed point precision. At iso-accuracy, QNNs using fewer bits require deeper and wider network architectures than networks using higher precision operators, while they require less complex arithmetic and less bits per weights. This fundamental trade-off is analyzed and quantified to find the minimum energy QNN for any benchmark and hence optimize energy-efficiency. To this end, the energy consumption of inference is modeled for a generic hardware platform. This allows drawing several conclusions across different benchmarks. First, energy consumption varies orders of magnitude at iso-accuracy depending on the number of bits used in the QNN. Second, in a typical system, BinaryNets or int4 implementations lead to the minimum energy solution, outperforming int8 networks up to 2-10× at iso-accuracy. All code used for QNN training is available from https://github.com/BertMoons/.

The assessment of networks is frequently accomplished by using time-consuming analysis tools based on simulations. For example, the blocking probability of networks can be estimated by Monte Carlo simulations and the network resilience can be assessed by link or node failure simulations. We propose in this paper to use Artificial Neural Networks (ANN) to predict the robustness of networks based on simple topological metrics to avoid time-consuming failure simulations. We accomplish the training process using supervised learning based on a historical database of networks. We compare the results of our proposal with the outcome provided by targeted and random failures simulations. We show that our approach is faster than failure simulators and the ANN can mimic the same robustness evaluation provide by these simulators. We obtained an average speedup of 300 times.

Predict software program reliability turns into a completely huge trouble in these days. Ordinary many new software programs are introducing inside the marketplace and some of them dealing with failures as their usage/managing is very hard. and plenty of shrewd strategies are already used to are expecting software program reliability. In this paper we're giving a sensible knowledge and the difference among those techniques with my new method. As a result, the prediction fashions constructed on one dataset display a extensive decrease in their accuracy when they are used with new statistics. The aim of this assessment, SE issues which can be of sensible importance are software development/cost estimation, software program reliability prediction, and so forth, and also computing its broaden computational equipment with enhanced power, scalability, flexibility and that can engage more successfully with human beings.

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.

Cloud computing is a revolution in IT technology that provides scalable, virtualized on-demand resources to the end users with greater flexibility, less maintenance and reduced infrastructure cost. These resources are supervised by different management organizations and provided over Internet using known networking protocols, standards and formats. The underlying technologies and legacy protocols contain bugs and vulnerabilities that can open doors for intrusion by the attackers. Attacks as DDoS (Distributed Denial of Service) are ones of the most frequent that inflict serious damage and affect the cloud performance. In a DDoS attack, the attacker usually uses innocent compromised computers (called zombies) by taking advantages of known or unknown bugs and vulnerabilities to send a large number of packets from these already-captured zombies to a server. This may occupy a major portion of network bandwidth of the victim cloud infrastructures or consume much of the servers time. Thus, in this work, we designed a DDoS detection system based on the C.4.5 algorithm to mitigate the DDoS threat. This algorithm, coupled with signature detection techniques, generates a decision tree to perform automatic, effective detection of signatures attacks for DDoS flooding attacks. To validate our system, we selected other machine learning techniques and compared the obtained results.

Vulnerability detection is an import issue in information system security. In this work, we propose the deep learning method for vulnerability detection. We present three deep learning models, namely, convolution neural network (CNN), long short term memory (LSTM) and convolution neural network — long short term memory (CNN-LSTM). In order to test the performance of our approach, we collected 9872 sequences of function calls as features to represent the patterns of binary programs during their execution. We apply our deep learning models to predict the vulnerabilities of these binary programs based on the collected data. The experimental results show that the prediction accuracy of our proposed method reaches 83.6%, which is superior to that of traditional method like multi-layer perceptron (MLP).