Search

The paper deals with a problem of the obfuscated JavaScript code detection and classification based on Abstract Syntax Trees (AST) coloring. Colors of the AST vertexes and edges are assigned with regard to the types of the AST vertexes specified by the program lexical and syntax structure and the programming language standard. Research involved a few stages. First of the all, a non-obfuscated JavaScript programs dataset was collected by the public repositories evaluation. Secondly, obfuscated samples were created using eight open-source obfuscators. Classifier models were built using an algorithm of gradient boosting on the decision trees (GBDT). We built two types of the classifiers. The first one is the model that classifies the program according to the type of the obfuscator used, i.e. based on what obfuscator created the sample. The second one tries to detect samples obfuscated by the obfuscator whose samples are not observed during training. The quality of the obtained models is on par with the known published results. The feature engineering method proposed in the paper does not require a preliminary analysis of the obfuscators and obfuscating transformations. In the final part of the paper we analyze a quality of models estimated, discussing the certain statistical properties of the obfuscated and non-obfuscated samples obtained and corresponding colored ASTs. Analysis of generated samples of obfuscated programs has shown that the method proposed in the paper has some limitations. In particular, it is difficult to recognize minifiers or other obfuscating programs, which change the lexical structure to a greater extent and the syntax to a lesser extent. To improve the quality of detection of this kind of obscuring transformations, one can built combined classifiers using both the method based on the AST coloring and the additional information about lexemes and punctuation, for example, entropy of identifiers and strings, proportion of characters in upper and lower case, usage frequency of certain characters etc.

To ensure many production processes are used compressors of various types, including turbochargers, which produce compressed air. The actual performance values of turbochargers used in highlands are significantly different from the certified values, and parameters of compressed air do not always guarantee the smooth and efficient functioning for consumers.The paper presents research results of the turbochargers of 4CI 425MX4 type, a series of "CENTAC", manufactured by INGERSOL – RAND Company. The research has been conducted in industrial highland conditions in difficult climatic environment. There were almost no investigations of turbochargers running in highland conditions. The combination of low atmospheric pressure with high temperature of the intake air causes the abnormal operating conditions of a turbocharger. Only N. M. Barannikov in his paper shows the results of theoretical studies of such operating conditions, but as to the practical research, there is no information at all.To normalize the turbocharger operation an option of the mechanical pressurization in the suction pipe is adopted. As a result of theoretical research, a TurboMAX blower MAX500 was chosen as a supercharger. The next stage of theoretical research was to construct characteristics of the turbocharger 4CI 425MX4 with a mechanical supercharger in the suction pipe. The boost reduces to the minimum the time of using additional compressors when parameters of the intake air are changed and ensures the smooth and efficient functioning for consumers.To verify the results of theoretical studies, namely, the technique for recalculation of the turbocharger characteristics under the real conditions of suction, were carried out the experimental researches. The average error between experimental and theoretical data is 2,9783 %, which confirms the validity of the technique used for reduction of the turbocharger characteristics to those under the real conditions of suction.

The paper describes results of analytical and experimental analysis of seventeen functions used for evaluation of binary classification results of arbitrary data. The results are presented by 2×2 error matrices. The behavior and properties of the main functions calculated by the elements of such matrices are studied. Classification options with balanced and imbalanced datasets are analyzed. It is shown that there are linear dependencies between some functions, many functions are invariant to the transposition of the error matrix, which allows us to calculate the estimation without specifying the order in which their elements were written to the matrices.It has been proven that all classical measures such as Sensitivity, Specificity, Precision, Accuracy, F1, F2, GM, the Jacquard index are sensitive to the imbalance of classified data and distort estimation of smaller class objects classification errors. Sensitivity to imbalance is found in the Matthews correlation coefficient and Kohen’s kappa. It has been experimentally shown that functions such as the confusion entropy, the discriminatory power, and the diagnostic odds ratio should not be used for analysis of binary classification of imbalanced datasets. The last two functions are invariant to the imbalance of classified data, but poorly evaluate results with approximately equal common percentage of classification errors in two classes.We proved that the area under the ROC curve (AUC) and the Yuden index calculated from the binary classification confusion matrix are linearly dependent and are the best estimation functions of both balanced and imbalanced datasets.

Описаны специализированные методы, разработанные авторами для решения задач обработки случайных точечных изображений, в основе которых лежат построение программных систем для проведения трудоемких аналитических выкладок и использование различных расширений классических чисел Каталана. Приведены примеры эффективного применения предложенных методов для расчета точных аналитических формул, описывающих вероятность безошибочного считывания случайных дискретных полей и цифровых изображений, проводимого сканирующей апертурой с ограниченным числом пороговых уровней., During the digital registration and subsequent processing of fast dynamic processes which have different physical nature, determination for the unknown coordinates of the point-pulse sources becomes one of the most time-consuming and algorithmically complex problems. It happens since it is necessary to satisfy the requirements for accuracy and reliability of registration in such tasks. Finding the exact analytical relationships connecting reliability of the registration with the characteristics of the physical process and the output parameters of the processing system is a problematic and very difficult task in most practically important cases, for example in the case of power of random radiation source and the size of the analyzed field. This paper proposes the methods developed by the authors for calculating the exact analytical formulas and relationships that describe the probability of error-free readout of a random point-pulse field when registration procedure is performed by a scanning aperture with a limited number of threshold levels. The specialized methods, based on the construction of software systems for laborious analytical calculations and the use of various extensions of the classical Catalan numbers are offered. In particular, procedures have been built for multidimensional integration over convex polyhedral areas with freely movable boundaries in n-dimensional space. Two probabilistic problems are also formulated, leading to an extension of the classical Catalan numbers, which turned out to be more convenient to formulate and solve in a symbolic-linguistic form., №5(23) (2018)

This article presents an algorithm for restoring broken pixels, which can appear in graphic files with statistical gaps. The suggested algorithm is based on the method of hierarchical analysis of the decision support theory. The choice of the broken pixel color depends on the nearest neighbors and their next neighbors. Three parameters inherent in each nearest neighbor are analysed. Firstly, it is the number of neighbors, which have the same color as the given nearest neighbor. Secondly, it is a deviation of the given pixel from the average value of its neighbors. Thirdly, it is a difference between the pixels being on the opposite sides of the broken pixel. Based on these three criteria, for each nearest neighbor of the broken pixel, a weight coefficient is defined. A hierarchical two-level tree for making decision is constructed. As a color of the broken pixel, its neighbor color with the maximum weight is chosen.A computer experiment to determine the effectiveness of the proposed method is conducted. The effectiveness of the proposed method was determined by comparing the similarity degree of the broken and restored images to the source image. To compare images Minkowski metric was used. To conduct experiments photographic and artificial images were used. The paper investigates a dependence of the proposed algorithm efficiency on the broken image amount. It was found out that the proposed algorithm has the advantage over the known algorithms for restoring broken pixels near the sharp edges. An image restored by our method has more sharply defined edges as compared to what the smoothing filters provide. The proposed method can be iteratively applied. As the experiments have shown, the first five iterations provide image enhancement.The proposed method together with the algorithms for detecting the broken pixels can be used to design filters of noisy images. The method efficiency enhancement can be achieved in case of taking into account the large number of neighbors in making decision. This method can be also developed using the increased number of criteria when making decisions.

International audience; http://mech.math.msu.su/~fpm/ps/k14/k143/k14303.pdfIn this paper, a computerized model for morphological analysis of languages with word-formation based on affixation processes is proposed. The main idea consists in defining structural patterns of words and corresponding lists of suffixes. First, a detaileddescription of a stemming algorithm, its modification, and the technique of determining grammatical characteristics of word-forms are given. The next part of this work focuses on the application of the proposed algorithms for the French language. Finally, some results of execution of these algorithms are provided.; http://mech.math.msu.su/~fpm/ps/k14/k143/k14303.pdfВ работе предлагается метод структурных схем в качестве модели морфологического анализа словоформ естественного языка с развитым аффиксальным словообразованием и словоизменением. Дано описание алгоритма выделения псевдоосновы, его модификация, а также алгоритм восстановления грамматических характеристик словоформ. Описано применение предложенного метода для анализа словоформ французского языка. Представлены результаты работы предложенных алгоритмов.

In this paper we describe an implementation of a method for blurred pictures restoring. We consider uniform, linear photo-camera shift (movement) while picture is taken. In this case, a picture, formed on a chip of a camera, is not static, but moving along some straight line, and as a result photo is blurred. Blurred picture can be seen as a convolution of two functions – one describes initial picture, another is point-spread (or blurring) function (PSF) [1]–[3]. “Deblurred” picture can be found as a deconvolution of the given picture with known PSF [1], [2]. To do this it is convenient to use Fourier transform and apply the convolution theorem. But it leads to division by 0, and thus the method is unstable. We suggest two heuristics to avoid division by 0 and compare them with the known one.