RESEARCH OF THE ISSUES OF IMPROVEMENT OF PROTECTION SYSTEMS AGAINST DDOS-ATTACKS BASED ON THE COMPREHENSIVE ANALYSIS OF MODERN INTERACTION MECHANISMS

The article presents the results of an analysis of the growth in the development of botnet networks and new cyber threats when they are used by cybercriminals. A review and comparison of the models for the implementation of botnet networks is carried out, as a result of which there are two main types. The main types of attacks carried out using the infrastructure of distributed computer networks are identified and classified, formed into 7 main groups, taking into account the relevance, prevalence and amount of damage. Based on the results of the analysis, it was determined that the most widespread and relevant type of attack is “Denial of Service”. The article presents a classification of services that provide services to ensure the protection of network resources from distributed attacks by the "Denial of Service" type, by the type of deployment, the level of security and the types of services provided. The comparison criteria are given taking into account their infrastructure, availability of technical support and a test period, available types of protection, capabilities, additional options, notification and reporting, as well as licensing. Practically implemented and shown a way to integrate the DDoS-Guard Protection service with an additional module at the application level, which made it possible to expand the methods of protection against DDoS attacks. Various modifications of the combined use of the module and the modified system make it possible to increase the expected level of detection and prevention of cyber - attacks.

AUTOMATED VULNERABILITY SEARCH IN A WEB APPLICATION BASED ON REINFORCEMENT LEARNING

We analyzed the urgency of the task of creating a more efficient (compared to analogues) means of automated vulnerability search based on modern technologies. We have shown the similarity of the vulnerabilities identifying process with the Markov decision-making process and justified the feasibility of using reinforcement learning technology for solving this problem. Since the analysis of the web application security is currently the highest priority and in demand, within the framework of this work, the application of the mathematical apparatus of reinforcement learning with to this subject area is considered. The mathematical model is presented, the specifics of the training and testing processes for the problem of automated vulnerability search in web applications are described. Based on an analysis of the OWASP Testing Guide, an action space and a set of environment states are identified. The characteristics of the software implementation of the proposed model are described: Q-learning is implemented in the Python programming language; a neural network was created to implement the learning policy using the tensorflow library. We demonstrated the results of the Reinforcement Learning agent on a real web application, as well as their comparison with the report of the Acunetix Vulnerability Scanner. The findings indicate that the proposed solution is promising.

RESEARCH OF IRP SYSTEMS BASED ON THE ANALYSIS OF MECHANISMS OF RESPONSE TO INFORMATION SECURITY INCIDENTS

The article discusses the features and functions of information security incident response systems. The analysis of modern IRP solutions is presented and the process of responding to typical incidents in systems of this class is described. Based on expert opinions, a list of criteria was formed, which were divided into groups by areas of functional responsibility for further comparison of the work of IRP systems. The assessment of the main and additional characteristics of IRP-systems was carried out using the formed criterion groups. The analysis of the comparison results showed that the most promising solutions are R-Vision IRP, IBM Resilient IRP and open-source solution - The Hive. The algorithm of the module for preventing phishing attacks was developed and presented, the software implementation of which was made using the Python language. As part of the integration capabilities of The Hive, a custom response function was implemented that not only potentially improved the system's performance in preventing phishing attacks, but also increased employee awareness of this threat. The result is an IRP system with personal flexible customization of individual elements and is the basis for the formation of the Security Center (SOC), which will bring the information security of organizations to a new level.

RESEARCH ON APPLICATION OF NEURAL NETWORKS FOR RESTORING DAMAGED VIDEO FILES OF AVI AND MP4 FORMATS

In the modern world, video files play a special role. The development of video compression algorithms and the growth of the Internet’s capabilities make it possible to transfer video files. Damage inevitably occurs when transferring video files. Accordingly, the question arises about restoring a damaged file and obtaining information from it. The article discusses the most commonly used video file extensions AVI, MP4. As a result of the study, it was revealed that the most common damage is in the headers, which leads to errors when opening files by players, data is damaged less often. Data corruption leads to the fact that a certain fragment of the video file is either played with errors, distortions, or is skipped. The article discusses the possibility of recovering damaged video file using the removal of undistorted data and proposes an algorithm for analyzing frames using a neural network. As part of the algorithm, a neural network is used to identify damaged frames in video data. The algorithm was implemented as a software product. For the first stage of checking the efficiency of the algorithm, deliberate distortions of one frame were made for each video file under study. As a result of experimental verification of the developed algorithm, it was revealed that it provides high accuracy in detecting distorted frame sequences.

AUTOMATION OF ELECTRONIC-PRINTING OFFICE WORK WITH THE DOCUMENTS IDENTIFICATION AND VERIFICATION

In the article the problem of electronic-printing office work, the documents identification and verification has been reviewed and analyzed. The technical feasibility of using algorithms for handwriting recognition, artificial intelligence and cryptography in electronic-printing office work has been substantiated. Authors are suggest an automated processing method of a paper document verification of its electronic counterpart authenticity. The algorithm of the alternative four-stage life cycle of the document and the method of its verification with the manual operations reduction and machine input are presented in detail. The structure of the integrated subsystem of machine input and documents verification used in the Edinaja informacionnaja sistema «Elektronniy Universitet» of an educational institution is presented. The results of the document automated processing and protection with training a multilayer convolutional neural network using the example of intermediate certification sheets were obtained. The possibility of applying the described methodology to strict reporting of a fixed structure documents with handwritten filling has been proved.

QUATERNION-BASED ATTITUDE CONTROL OF HIGHLY MANEUVERABLE UNMANNED UNDERWATER VEHICLE

Traditionally, unmanned underwater vehicles are operated at low angles of inclination (pitch and roll). However, there are tasks that require high maneuverability and controllability of the underwater vehicle in the entire range of orientation angles. At the same time, traditional control systems use the Euler angles and have limitations associated with the degeneration of the kinematic equations at a picth angle of ± 90 °, the problem of the non-uniqueness of the Euler angles, and the deterioration of the system performance at large inclinations of the vehicle. Thus, the question of developing a synthesis method for a control system for highly maneuverable unmanned underwater vehicles arises. The paper provides a review and comparative analysis of existing approaches to attitude control, on the basis of which an approach using quaternions is chosen. The law of attitude control based on quaternions was approved during field tests on a hybrid unmanned underwater vehicle "Iznos", developed at Bauman Moscow State Technical University. The results obtained during the tests are given in the article. The quaternion-based approach has better performance in comparison with the traditional control system. In addition, control system based on quaternion approach has a simple structure and can be used to increase the maneuverability of unmanned underwater vehicles with average requirements for positioning accuracy.

APPLICATION OF FACE RECOGNITION TECHNOLOGIES IN CONTROL AND ACCESS CONTROL SYSTEMS

The article shows the relevance of the widespread use of computer vision technology on the example of face recognition as part of the access control and management system. The main methods that are used in the implementation of classical control systems and access control are considered. The scheme for the implementation of the access control with face recognition technology is described. The use of this technology makes it possible to increase the level of information security of enterprises and, as a result, reduce the possible financial damage from the implementation of attacks on their assets from illegitimate penetration into the protected area through the access control system using the passes of legal users.

STRUCTURE OF A SOFTWARE PRODUCT FOR SEMANTIC ANALYSIS OF TEXTUAL INFORMATION

The article is devoted to the development of software for semantic text analysis. Describes the General logic of the developed web application, which implements the classification of textual information by previously predefined semantic categories. This article provides usage and deployment diagrams, as well as a General diagram of the algorithm. The methods implemented in the app allow you to increase the speed of processing text information. The use of the developed software product allows you to quickly process text information of any content, as well as conduct a deeper semantic analysis of the text. The implemented method is relevant in many areas of activity where you have to work with text information: monitoring of emotional mood towards the company, marketing, social network analysis.

DEVELOPMENT OF THE MODULE FOR DATA MANAGEMENT ON OBJECTS FOR ONLINE MAP OF A CITY

The solution of a wide range of tasks aimed at ensuring the sustainable functioning of urban infrastructure requires a comprehensive forecast of the development of the situation. The operation of distributed technical systems in an urbanized area is directly related to multiple subject - object interactions, since system components are most often located close to the almost continuous activity of people related to their maintenance, or just engaged in their daily routine. Therefore, the construction of urban processes models requires an extensive information base about the area infrastructure objects. First of all, this is associated with the aggregation and unification of data from disparate sources, and further verification, addition and updating of the original data is required. The paper describes the stages of development of a data management software module that parses data from a file with OSM XML format, transforms them into the necessary structure for working within a single spatial modeling platform Live.UrbanBasis.com and makes procedural generation of missing data. The approach to additional data generation of infrastructure objects is demonstrated using the example of entrances, floors, and apartments. The paper reveals the approaches and technologies used to work with the data of the OpenStreetMap web mapping project.

INFORMATION SUPPORT FOR DECISION-MAKING IN THE PRODUCTION OF THE CATALYST FOR THE SYNTHESIS OF CARBON NANOTUBES

The aim of the study is to develop information systems for supporting and supporting decision-making in the production of a metal oxide catalyst that provides targeted synthesis of carbon nanotubes by gas-phase chemical deposition. To achieve the goal, the following tasks were solved: a new approach to the process of creating a catalyst for the thermal decomposition of unstable compounds for synthetic nanotubes was developed; experimental studies of the effect on the post-thermal treatment of the catalyst and its precursors by physical action (ultrasonic, electromagnetic and microwave fields, etc.), which were obtained the approximating characteristics of the synthesized models of carbon nanostructures on the parameters of the process of pre- and post-thermal treatment of the catalyst were used to create a recommendation module. On the basis of the results obtained, blocks of implementation and technologies were developed, used in the creation of a system for maintaining and supporting solutions for the production of a catalyst for synthetic nanotubes. The application of the developed system of maintenance and support of decisions makes it possible to form a catalyst that makes it possible to synthesize carbon nanotubes with specified characteristics. Also, the use of this information system in the production of a catalyst helps to expand the range of synthesized nanoproducts in the process of gas-phase chemical deposition without changing the composition of the catalyst.