Methodology for constructing a neural fuzzy network in the field of information security

This paper proposes the use of hybrid models based on neural networks and fuzzy systems to build intelligent intrusion detection systems based on the theory of fuzzy rules. The presented system will be able to generate rules based on the results using fuzzy logic neurons. To avoid oversaturation and assist in determining the necessary network topology, training models based on extreme learning machine and regularization theory will be used to find the most significant neurons. In this paper, a type of SQL injection cyberattack is considered, which actively exploits errors in systems that communicate with the database via SQL commands, and for this reason is considered a kind of straightforward attack. The fuzzy neural network architecture used in detecting SQL injection attacks is a multi-component structure. The first two layers of the model are considered as a fuzzy inference system capable of extracting knowledge from data and transforming it into fuzzy rules. These rules help build automated systems for detecting SQL injection attacks. The third layer consists of a simple neuron that has an activation function called a leaky ReLU. The first layer consists of fuzzy neurons, the activation functions of which are Gaussian membership functions of fuzzy sets, defined in accordance with the partitioning of the input variables. The technique uses the concept of a simple linear regression model to solve the problem of choosing the best subsets of neurons. To perform model selection, the paper used the widely used least angular regression (LARS) algorithm.

Analysis of the detection of an attack based on SQL injection using an impulse artificial neural network

This article presents the results of testing to create a specialized system that helps prevent cyberattacks, thus popularizing the construction of intelligent applications. Based on the results obtained, it can be argued that the tests carried out are satisfactory. The mathematical basis for building a neural network model is the HESADM model (Hybrid Artificial Intelligence Framework). The presented system allows you to form a set of rules using fuzzy logical neurons. This paper presents an approach to the formation of a fuzzy neural network used for detecting SQL injection attacks. The methodology used in this paper is an impulse artificial neural network (SANN), which uses an evolving neural network system (eCOS) and a multi-layer approach of an impulse artificial neural network to classify the exact type of intrusion or network anomaly with minimal computational potential. The impulse artificial neural system forms itself continuously, adapting to the input data, being in a functioning or not state, being under the supervision of an administrator. This system finds application to several other complex problems of the real world, proving its efficiency, including in the field of information security. The considered model is a hybrid evolving pulse anomaly detection model (HESADM), which works on impulses that occur in the system, while neurons are used to monitor the algorithm using a single training pass. In the system, traffic-oriented data is used by importing classes that use variable encoding. The data used is obtained by converting the real characteristics of network traffic into certain time stamps.

Calculation of the regulator for the object with a delay

The task of managing some systems is complicated due to the fact that real technical objects contain delay links. That is, there is a certain period of time when there is no reaction from the object of regulation to the control action. Usually, the presence of a delay link negatively affects the quality of management of such a system. There are various ways to synthesize a control system for such systems. These include: Smith predictors, specialized control tuning algorithms, the use of self-adjusting systems with active adaptation. However, they impose additional requirements on the dynamics of the system or are complex in technical implementation and configuration. Within the framework of this article, an attempt is made to calculate the regulator by the polynomial method for an object with a delay. The mathematical model of the delay is obtained by approximating the delay link next to the Pade. To ensure the necessary dynamics of the transition process from the system, we require the preservation of the poles of the delay link. Then the regulator, calculated for a system with a delay link in the form of a series of Pads, is applied to a system with an "ideal" delay. For clarity of the calculations carried out, an object in the form of a combination of aperiodic and integrating links connected in different ways is taken as an example. The integrating link is necessary to give the system astatic properties. As a delay, we will use the approximation of the range of different orders. The link of delay gives the system a non-stable character.

Polynomial method for the synthesis of regulators for the special case of multichannel objects with one input variable and several output values

Currently, an urgent task in control theory is the synthesis of regulators for objects with a smaller number of input values compared to output ones, such objects are described by matrix transfer functions of a non-square shape. A particular case of a multichannel object with one input variable and two / three / four output variables is considered; the matrix transfer function of such an object has not a square shape, but one column and two / three / four rows. To calculate the controllers, a polynomial synthesis technique is used, which consists in using a polynomial matrix description of a closed-loop control system. A feature of this approach is the ability to write the characteristic matrix of a closed multichannel system through the polynomial matrices of the object and the controller in the form of a matrix Diophantine equation. By solving the Diophantine equation, the desired poles of the matrix characteristic polynomial of the closed system are set. There are many options for solving the Diophantine equation and one of them is to represent the polynomial matrix Diophantine equation as a system of linear algebraic equations in matrix form, where the matrix of the system is the Sylvester matrix. The choice of the order of the polynomial matrix controller and the order of the characteristic matrix is carried out on the basis of the theorem given in the works of Chi-Tsong Chen, which always holds for controlled objects. If the minimum order of the controller is chosen in accordance with this theorem, and the Sylvester matrix has not full rank, then this means that there are more unknown elements in the system of linear algebraic equations than there are equations. In this case, the solution corresponding to the selected basic minor has free parameters, which are the parameters of the regulators. Free parameters of regulators can be set arbitrarily, which is used to set or exclude some zeros in a closed system. Thus, using various examples of objects with a non-square matrix transfer function, a polynomial synthesis technique is illustrated, which allows not only specifying the poles of a closed system, but also some zeros, which is a significant advantage, especially when synthesizing controllers for multichannel objects.

About the role of public organizations in the structure of the housing and communal services system

The practice of public associations entering various spheres of activity in the territories of the state shows that many associations do not fulfill their missions to ensure a comfortable stay for the citizens of the territories, but are engaged in consumer extremism. They solve their consumer tasks and systematically do not participate in the processes of constructive interaction between the authorities, producers and consumers of services. In this article, for the first time, the issues of interaction of public associations in the housing and communal services system with all the elements available in it are considered. The existing structure of the housing and communal services system is shown, which includes such elements as: federal, regional authorities, resource-supplying, related organizations, regional operators in the field of housing and communal services, performers of housing and communal services, public associations and homeowners and tenants. The stages of the organization of public associations are defined, a block diagram of the algorithm of state registration and registration of a legal entity for public associations is constructed. The internal organizational and managerial structure of associations is shown, their functions and their place in the housing and communal services management system are considered. It should be emphasized that the influence of public organizations is carried out through internal and external management in the housing and communal services system to solve the tasks of promoting the formation of housing self-government as an important institution of civil society and an effective tool for improving the housing and communal industry. It is revealed that an essential tool in the management of the housing and communal services system is the presence of public microstructures in the majority of its elements, interaction with which makes it possible to exert a controlling influence on the entire system as a whole, thereby obtaining positive results in protecting the rights of consumers of housing and communal services.

Model of the "biometry-code" converter based on artificial neural networks for analysis of facial thermograms

Existing asymmetric encryption algorithms involve the storage of a secret private key, authorized access to which, as a rule, is carried out upon presentation of a password. Passwords are vulnerable to social engineering and human factors. Combining biometric security techniques with cryptography is seen as a possible solution to this problem, but any biometric cryptosystem should be able to overcome the small differences that exist between two different implementations of the same biometric parameter. This is especially true for dynamic biometrics, when differences can be caused by a change in the psychophysiological state of the subject. The solution to the problems is the use of a system based on the "biometrics-code" converter, which is configured to issue a user key after presentation of his/her biometric image. In this case, the key is generated in advance in accordance with accepted standards without the use of biometric images. The work presents results on using thermal images of a user for reliable biometric authentication based on a neural network "biometrics-code" converter. Thermal images have recently been used as a new approach in biometric identification systems and are a special type of biometric images that allow us to solve the problem of both the authentication of the subject and the identification of his psychophysiological state. The advantages of thermal imaging are that this technology is now becoming available and mobile, allowing the user to be identified and authenticated in a non-contact and continuous manner. In this paper, an experiment was conducted to verify the images of thermograms of 84 subjects and the following indicators of erroneous decisions were obtained: EER = 0.85 % for users in the "normal"state.

Sine waves frequency identification system modeling based on artificial network operation

Sine wave contribution can be observed in many casual periodic processes- starting with nature and finishing with complex hand-made processes like social, economic, technical and biological. This sphere of science have been staying under strict society attention thus having promoted and developed different theories, based on discrete Fourier transform, least squares methods and so on. Technical problem in question can be represented by the list of different processes of wave nature, e.g. sound and light occurrence, wave motion of different mediums. One of the most actual problems in question examples is marine sine wave impact identification for the marine ship main engine speed of rotation adjustment– the process, where control object inevitably is subject to load impact fluctuations. Especially evident this object can be concerned for the Northern Sea Route area, where climate severity is next to the states freights turnover increase desire. In this case marine main engine speed of rotation adjustment without specific control algorithm can be considered to be ineffective because of efficiency drops, increased parts and facilities run-outs. That is why, due to neural networks integration trend into industry processes, we tried to attempt building a separate neural network for defining the frequency of a noisy low-frequency sine wave. The obtained results [1] proved sine waves frequency identification possibility with the help of artificial network, however accuracy was found to be unacceptable because of sketchy algorithm elaboration and small learning array size.

Honeypot as a tool for creating an effective secure system

In the presente work, the theoretical aspects of honeypot systems were considered, and the classification of honeypots on various grounds was presented. The architecture of a honeypot system is presented, designed to investigate the behavior of an attacker after his penetration into the corporate system, as a tool for implementing a complex effective secure system of the organization.

Model for assessing the qualification of IT specialists in software development

The decisive factor for the successful work of modern IT organizations is the professional qualities of the personnel and the system for its development. Staff training for software development organizations is of particular importance due to the fact that activities in this field make high demands on the level of qualifications of employees, their knowledge and skills, while they tend to quickly lose their relevance. However, there are problems in the assessment of personnel qualifications that can affect its’ objectivity and the effectiveness of further management decisions, for example: favoritism, bias, high exactingness, an erroneous standard. The purpose of the work is to develop a model for assessing the qualifications of IT specialists in the field of software development. . This study investigates personnel assessment system, types of criteria for assessing the qualifications of software developers and testers, which cover technical aspects of activities, interpersonal and mental characteristics of specialists. To assess the qualifications, a model of the conceptual theory of software development competence was selected and changed. Based on a literature review, analysis of vacancies and interviews with IT specialists, the main areas of activity of developers and testers were identified, as well as characteristics that need to be assessed. Based on the modified model, a prototype of the system was developed in the JavaScript programming language and on the Node JS software platform for collecting information, which loads data from the Atlassian Jira version control systems for further evaluation.

Compiler from El programing language: improvement and development

The implementation of the new multi-paradigm (functionally- imperative) programming language El, developed at the Department of Computer Science of the Novosibirsk State Technical University, in the form of a compiler is associated with the need to find ways to solve a number of complex problems. The current version of the compiler does implement only partially functionality of the language and generates far from optimal executable codes. In this paper, we consider the problem of an efficient compilation of an El-program, taking into account the need to implement new high-level data structures (two-sided lists, vectors with special forms of access, and a number of others) and control structures of the language, which make it possible to uniformly define cyclic and branching computational processes, as well as those laid down in the language a mechanism for explicitly controlling the mutability of variables. The tasks of improving and developing a compiler organized according to the classical multi-platform scheme are briefly considered, in which the front-end (lexical, syntactic, and semantic analyzers) converts the program to be translated into pseudocode of a single format, and used efficient infrastructure for building LLVM compilers as a back-end that turns pseudocode into executable code for different platforms. Execution of all possible operations on elements of high-level data structures (lists, tuples, vectors), as well as on arbitrary-precision numbers, has been moved to the runtime support library and, accordingly, can be deeply optimized. For this structure, the outlined ways of solving the problem of developing and improving the compiler by deep reforming and optimization of the chain of transformations of the translated program implemented by the front-end are formulated. At the initial stage, it is planned to implement a new compiler for two platforms: Linux and Windows.