Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Elena Revyakina has a total of 49 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Intelligent Facial and Emotion Recognition System for the Predictive Assessment of Socially Dangerous Behavior

    by E. A. Revyakina, A. R. Gazizov, Е. А. Ревякина, А. Р. Газизов

    Objective. This article addresses the automation of monitoring in public spaces to facilitate the early detection of signs of socially dangerous behavior. Method. The system is built upon a multi-level computer vision pipeline that integrates state-of-the-art open-source neural network models: InsightFace for face detection and embedding generation; DeepFace and FER as independent emotion classifiers; and MediaPipe Face Mesh for the geometric analysis of facial expressions. Result. An intelligent face and emotion recognition system has been developed to predict the risk of conflict in crowded public areas. A key feature of this solution is an adaptive buffering and frame-selection mechanism, which isolates the most informative images for subsequent analysis. This significantly enhances the system's robustness in real-world conditions, such as varying lighting, diverse viewing angles, and partial occlusions. A crucial aspect of the design is the implementation of "privacy by design" principles: data processing is localized, biometric features are represented as anonymized embeddings, and a multi-level, role-based access control model is applied to sensitive data. Conclusion. The developed system demonstrates practical utility as a predictive analytics tool for security services, enabling a shift from reactive surveillance to the proactive identification of potentially dangerous situations.

  • Open Access

    Slowloris DDoS Defense Mechanism

    by P. V. Razumov, L. V. Cherkesova, E. A. Revyakina

    Objective. The objective of this study is to perform a software analysis of the Slowloris cyberattack and implement a protection mechanism against a Slowloris-type DDoS attack. Method . PHP was chosen for the development of the software tool, as it has established itself as one of the most popular and widely used languages in web development. The PhpStorm IDE from JetBrains was also selected along with the programming language. Result. A software mechanism for protection against a Slowloris-type DDoS attack has been developed. The mechanism has several advantages over similar approaches: the software can be used free of charge and is modifiable; it meets modern password strength requirements; it uses the HTTPS protocol for secure connections; it encrypts requests; it hashes user authorization data (login, password) and stores it in a database on the server, etc. Conclusion . The developed software tool can be used as an embedded protection mechanism for any authorization or registration pages, allowing for the automatic blocking of potentially dangerous connections.

  • Open Access

    Merkle's post-quantum signature based on the modified Lamport algorithm

    by Larisa Vladimirovna Cherckesova, Elena Aleksandrovna Revyakina, Nikita Genad'EVich Lyashenko

    The development of a Merkle post-quantum signature scheme based on a modified Lamport one-time signature algorithm is presented. The Merkle signature algorithm and the Lamport one-time signature algorithm are described. There is also a review of the current literature on the subject of the Merkle signature algorithm. A modified algorithm for Lamport's one-time electronic digital signature is described. The algorithms for key generation, signature generation, and verification of a previously generated signature are described in detail. The paper presents a software implementation of an electronic digital signature system with a graphical interface based on the developed algorithm, which allows key generation, signature generation and verification. A flowchart is provided for each of the main modules of the program, and the graphical interface of the developed software for each module is also demonstrated. The results of testing the modified algorithm are presented and its performance is compared with the standard algorithm. The test results confirm that using the modified algorithm allows faster verification of messages, while the speed of key generation and signature does not increase in comparison with the standard algorithm. The modified algorithm speeds up verification regardless of the message length. The results of the performed research are a modified Lamport one-time signature algorithm, which provides a higher signature verification rate compared to the classical algorithm, and a software tool with a graphical interface for generating and verifying a post-quantum electronic digital signature.

  • Open Access

    System analysis and information processing to solve the problem of detecting breakdowns of computer information storage

    by N. M. Kodatsky, E. A. Revyakina, A. R. Gazizov

    Objective. One of the important aspects of maintaining the efficient operation of information systems is the condition of computer equipment. The purpose of the study is to describe a method for effective system analysis of the state of a computer's information storage device. Method. The study is based on the use of machine learning algorithms to analyze and interpret data obtained from SMART tests. Includes a comprehensive analysis and experimental study. It involves conducting experiments with a data set and the Google Colab cloud environment, creating and analyzing a machine learning model, and evaluating the effectiveness and quality of training. Result. A tool for assessing the state of computer equipment based on the Random Forest algorithm has been developed using historical data from SMART tests. Conclusion. The results not only allow the implementation of a working data analysis tool in the field of computer equipment maintenance, but also contain a practical example of increasing the reliability and efficiency of information systems. The results are useful for IT specialists and for organizations optimizing equipment maintenance processes and increasing competitiveness.


  • Open Access

    Creation of an encryption algorithm resistant to attacks through side channels of leakage

    by Larissa Cherckesova, Elena Revyakina, Olga Buryakova, Andrey Gazizov

    The paper is devoted to.the development of an encryption algorithm resistant to leakage through side channels The objectives of the work were the development and computational-experimental justification of the algorithm. Materials and methods. A new algorithm of encryption resistant to attacks through side channels is proposed.The algorithm resistance to attacks on the basis of numerical experiments is analyzed.As a result of analyzing statistical data before and after modifications of the algorithm it was found that the developed algorithm is resistant to time and energy attacks. Results of the study.The main result of the work is the development of an encryption algorithm resistant to attacks through side leakage channels. The resilience of the algorithm to attacks was confirmed by analyzing the statistical data before and after modifications to the algorithm. The comparisons concluded that the developed algorithm is resistant to timing attack and power consumption attack. Discussion and Conclusion. The resulting algorithm can be applied to counter groups of attacks on cryptographic devices, in which the attacker tries to obtain any information useful to him, through the physical features of the implemented cryptosystem.


  • Open Access

    Creation and Training of artifical neural network for Detection and Neutralization of Network DDos–attacks(“Denial of Service”)

    by P. V. Razumov, L. V. Cherkesova, E. A. Revyakina

    Objective. The goal of the research is to develop an artificial neural network (ANN) to detect and neutralize network DDoS attacks.Method. The research is based on the use of the Python programming language in an environment that supports the training functions of PyCharm neural networks.Result. An analysis of existing artificial neural networks was carried out to determine their optimal structure; Existing methods for detecting network DDoS attacks have been studied; Datasets were collected and refined to improve the quality of training; The structure of the artificial neural network of the classifier was created and its training was carried out, a demonstration software was created that illustrates the process of classification and blocking and neutralizing DDoS attacks.Conclusion. Having systems to monitor traffic, a Web application firewall, speed limiting, a status page, and a company face to answer questions on social media will all help ensure the most effective protection against DDoS attacks.


  • Open Access

    RETRACTED: Using machine learning to forecast hard drive failures

    by Nikita Kodatsky, Elena Revyakina, Andrei Gazizov, Vitaliy Gunko

    See the retraction notice E3S Web of Conferences 549, 00001 (2024), https://doi.org/10.1051/e3sconf/202454900001


  • Open Access

    The development of countermeasures against session hijacking

    by Larissa Cherckesova, Elena Revyakina, Evgeniya Roshchina, Vitaliy Porksheyan

    This article provides information about Session Hijacking and discusses countermeasures to prevent Session Hijacking attacks. In modern web applications and sites much vulnerability, which developers often do not pay attention to, are occurred. The paper presents a practical implementation of one of the attacks (MITM), and also proposes methods to counteract and protect against most types of attacks. The main purpose of this paper is to study Session Hijacking attacks and to propose countermeasures against them and existing vulnerabilities.


  • Open Access

    Circuit engineering solutions for high - temperature analog microcircuits in extreme environmental conditions

    by Alexandr Dzhurov, Kirill Lyashenko, Elena Revyakina, Larissa Cherckesova

    The current geopolitical situation and import–substitution challenges facing the domestic electronics industry require the creation of devices capable of reliably functioning in extreme environmental conditions, at particularly high temperatures. When developing electronic devices that must function reliably in temperature range beyond the usual values, developers should rely on cooling, active or passive. There may be situations when cooling is impractical or impossible. The operation of the device in special temperature range, in some situations, makes perfect sense if it provides reduction in the cost of the device or increase in its reliability. In such situations, it is necessary to solve many complex problems, including semiconductor manufacturing technology, design and testing methods. The article examines the issues of creating high–temperature electronics components necessary for the long-term development of the domestic oil–and–gas and aerospace industries. Creation of import-substituting technologies for intelligent wells makes it possible to reduce significantly the cost of equipment. In aerospace industry, this problem is even more actual: the cost of “western” computing devices for use in space reaches half million euros, and under the conditions of sanctions, its purchase may not be available, while similar import-substituting domestic device is up to 10 times cheaper. Flights to near and far space require, in addition to high radiation resistance, the reliability of all spacecraft systems in the wide temperature range. Article presents technical characteristics of the main analog chips designed to operate at temperatures up to +125 ° C.


  • Analysis of Technical Solutions for the Creation and Development of the Quantum Internet

    by Kirill Lyashenko, Larisa Cherkesova, Elena Revyakina, Boris Akishin, Tatiana Nikishina