Problems of information security. Computer systems

RAR RUS 9-19 0000-0002-0950-901X Vedernikov Yuriy vedernikov.yura@yandex.ru

St. Petersburg State Maritime Technical University

0000-0001-6695-2328 St. Petersburg State Marine Technical University Garkushev Alexander sangark@mail.ru St. Petersburg State Maritime Technical University Lipis Alexey dlipis@smtu.ru 0000-0001-9665-0128 Peter the Great St. Petersburg Polytechnic University Suprun Alexander afs54@inbox.ru

Russia, 195251, St. Petersburg, Polytechnicheskaya str., 29

Reconfiguration of the system development model information security management: interaction of base modules with the operator The article is devoted to the study of the possibility of modernizing the information security management systems of industrial enterprises by applying modern optimization methods. In addition to discrete deterministic values of parameters that reflect the influence of various factors on information security, propose to take into account heterogeneous indicators specified numerically, interval, verbally and using parametric series. A model of implementation in the form of a program that allows you to make an informed choice of the best of the alternatives. 10.48612/jisp/amv1-kdnf-zaae 004.942 information security model optimization ranking priority system preference matrix https://jisp.spbstu.ru/article/2024.16.1/ 2024_2_rus.pdf

RAR RUS 20-30 Jet Infosystems Markov Georgy 0000-0002-2264-7513 Peter the Great St. Petersburg Polytechnic University Krundyshev Vasiliy krundyshev_vm@spbstu.ru 13103571000 0000-0002-0232-7248 Peter the Great St. Petersburg Polytechnic University Zegzhda Dmitry zegzhda_dp@spbstu.ru

Russia, 195251, St. Petersburg, Polytechnicheskaya str., 29

Mathematical model of information security event management using Markov chain in industrial systems This paper examines the problem of ensuring information security in industrial Internet of Things systems. The study found that in order to comprehensively protect the information perimeter of an industrial enterprise from external and internal threats, in most cases information security event and incident management systems (SIEM systems) with customized rules for correlating events in the information infrastructure are used. At the same time, there is a need to create a mathematical apparatus that allows one to accurately and objectively assess the effectiveness of the SIEM system. As a result of the study, the problem of preventing information security incidents in industrial Internet of Things systems was formalized based on the developed mathematical model for managing information security events using a continuous-time Markov chain. 10.48612/jisp/vzkp-rbuh-xd9m 004.056 mathematical model industrial Internet of things information security event management Markov chains SIEM system https://jisp.spbstu.ru/article/2024.16.2/ 2024_2_rus.pdf

RAR RUS 31-43 0000-0001-6753-2181 Saint Petersburg Federal Research Center of Russian Science Academy Lebedev Ilya isl_box@mail.ru 0000-0003-1798-8257 Russian State Hydrometeorological University Sukhoparov Mikhail mail@sukhoparovm.ru 0009-0008-0128-4144 Tikhonov Daniil tikhonovdanil@gmail.com

Saint-Petersburg Federal Research Center of Russian Science Academy

Quality improvement of information security events identification through input data splitting The processing of information sequences using segmentation of input data is proposed, aimed at improving the quality of detection of destructive influences using machine learning models. The basis of the proposed solution is the division of data into segments with different properties of the objects of observation. A method using a multi-level data processing architecture is described, where learning processes are implemented at various levels, the analysis of the achieved values of quality indicators and the assignment of the best models for quality indicators to individual data segments. The proposed method makes it possible to improve the quality indicators for detecting destructive information influences by segmenting and assigning models that have the best performance in individual segments. 10.48612/jisp/znn9-1vat-6xdp 004.048 information security machine learning data set data sampling data segmentation processing models https://jisp.spbstu.ru/article/2024.16.3/ 2024_2_rus.pdf

RAR RUS 44-56 0000-0002-2765-0973 Safiullina Lina SafiullinaLKh@corp.knrtu.ru

Kazan National Research Technological University

0000-0001-8927-9113 Kasimova Alina KasimovaAR@corp.knrtu.ru

Kazan National Research Technological University

0000-0002-6119-1934 Alekseeva Anna annank90@mail.ru

Kazan National Research Technological University

Analysis of the reliability of storing templates when introducing modern biometric technologies into information security systems Currently, it can be argued that in certain areas of information technology, there is a complete replacement of classical computer system user authentication systems based on passwords and tokens with biometric technologies. However, biometric systems are vulnerable to various types of security threats. For example, in them, unlike the same passwords and tokens, templates based on biometrics cannot be replaced in case of compromise. To solve this problem, new protection schemes have been developed. Conventionally, they can be divided into two groups: biometric cryptography and cancelable biometrics. Biometric cryptography methods show average values of errors of the first and second types; experimental work in this area is widely known. Cancelable biometrics can be highly reliable, but there is not much experimental data on them. This paper presents a comparative analysis of the reliability of existing methods. It is shown that among the static biometric parameters the greatest interest is the iris, and among the dynamic ones – the keyboard stroke. However, using these methods, like others, has its own difficulties and risks. 10.48612/jisp/2hkg-u23v-g9xv 004.93, 64.066.8 identification authentication biometrics template biometric cryptography cancelable biometrics https://jisp.spbstu.ru/article/2024.16.4/ 2024_2_rus.pdf

RAR RUS 57-65 0000-0003-0374-4649 Peter the Great St. Petersburg Polytechnic University Sergadeeva Anastasia nsspbpoly@gmail.com 0000-0003-2849-4682 Peter the Great St. Petersburg Polytechnic University Lavrova Daria lavrova_ds@spbstu.ru

Russia, 195251, St. Petersburg, Polytechnicheskaya str., 29

0000-0002-7485-4848 Peter the Great St. Petersburg Polytechnic University Aleksandrova Elena aleksandrova_eb@spbstu.ru Countering steganalysis based on generative adversarial networks The paper proposes the generative adversarial network approach to improve the robustness of the steganographic method against modern stegoanalyzers. The approach is based on the joint operation of generative adversarial network, pixel importance map and least significant bit replacement method. The results of experimental studies confirmed the effectiveness of the proposed approach. 10.48612/jisp/aara-dg74-ata6 004.056 generative adversarial networks steganography steganography method steganalysis machine learning https://jisp.spbstu.ru/article/2024.16.5/ 2024_2_rus.pdf

RAR RUS 66-72 0000-0001-6377-5581 Admiral S.O. Makarov State University of Marine and River Fleet Baryshnikov Sergey barychnikovso@gumrf.ru Admiral S.O. Makarov State University of Marine and River Fleet Sakharov Vladimir saharovvv@gumrf.ru 57200960264 0000-0001-6289-3295 Russian State Hydrometeorological University Sikarev Igor sikarev@yandex.ru

Russia, 192007, St. Petersburg, Voronezhskaya str., 79

0000-0003-0554-5790 Admiral Makarov State University of Maritime and Inland Shipping Abramov Valery val.abramov@mail.ru Shnurenko Anatoly dock@ksz.spb.ru

«Kanonerskiy Ship Repair Plant» CJSC

Automation of ship repair management Tools development results for automating ship repair management processes are presented. It is indicated, that development of adequate and stable model and the choice of algorithms for its use are of key importance, their correctness is shown. 10.48612/jisp/a6v5-3det-fzv9 681.5.011 automation management ship repair model https://jisp.spbstu.ru/article/2024.16.6/ 2024_2_rus.pdf

RAR RUS 73-83 0000-0003-4322-3223 Admiral Makarov State University of Maritime and Inland Shipping Egorova Kristina natashov1397@mail.ru Admiral Makarov State University of Maritime and Inland Shipping Glebov Nikolay glebovnb@gumrf.ru 0000-0001-7648-5321 Admiral Makarov State University of Maritime and Inland Shipping Goloskokov Konstantin goloskokovkp@gumrf.ru Automated system for monitoring and predicting the spread of oil spills in aquatic environment using a group of UAVs This article is dedicated to studying the spreading of oil spills in the aquatic environment and developing a corresponding monitoring system using a group of unmanned aerial vehicles. To effectively control and prevent the spread of oil spills in water bodies, the process of comprehensive monitoring and forecasting needs to be automated. The foundation of such an automated system lies in mathematical models that enable the assessment of spill parameters, prediction of its trajectory, and determination of strategies to prevent and mitigate associated issues. The automation of monitoring and forecasting allows for continuous observation of the state of water resources and swift response to potential oil leaks. With the help of specialized sensors, unmanned aerial vehicles, and other technical means, it is possible to monitor changes in water conditions, detect the presence of oil spills, and determine their sizes. By possessing the ability to promptly respond to spills, the system ensures proper containment of leaks and minimization of negative environmental impact, as well as enables the development of strategies to prevent similar incidents in the future 10.48612/jisp/7bff-vvhf-p294 681.5, 004.9 oil spills water environment unmanned aerial vehicles automation monitoring system forecasting environmental protection https://jisp.spbstu.ru/article/2024.16.7/ 2024_2_rus.pdf

RAR RUS 84-94 Peter the Great St. Petersburg Polytechnic University Gavva Georgij gavva.gd@edu.spbstu.ru 0000-0002-9732-0099 Peter the Great St. Petersburg Polytechnic University Kalinin Maxim max@ibks.spbstu.ru

Russia, 195251, St. Petersburg, Polytechnicheskaya str., 29

Ensuring the connectivity and functional integrity of wireless reconfigurable networks by rebuilding the topology using an improved method of network game A comparative analysis of methods for protecting reconfigurable wireless networks that implement topology re-building was carried out, which made it possible to determine the network game method as the most promising in solving the task of maintaining the network connectivity and functional integrity. Managing the network topology when using the basic network game method is characterized by overloading the channels of the control node and excessive sensitivity to changes in network connections. In this research, the basic method is extended with the criterion of the maximal possible path length, which allows reducing the number of network reconfigurations when there is a short route between nodes passing through existing connections. It is experimentally shown that the improved method provides protective online restructuring of a network with lower topology rebuilding costs 10.48612/jisp/tdnx-gf17-e1e5 004.056 wireless reconfigurable network gaming approach network game reconfiguration path length functional integrity https://jisp.spbstu.ru/article/2024.16.8/ 2024_2_rus.pdf

RAR RUS 95-103 0009-0006-6856-2108 Peter the Great St. Petersburg Polytechnic University Pahomov Maksim pahomov_ma@spbstu.ru 0000-0003-1345-1874 Peter the Great St. Petersburg Polytechnic University Pavlenko Evgeny pavlenko_eyu@spbstu.ru Ensuring information security of vanets based on early detection of malicious nodes The features of VANETs are considered. An approach to ensuring the information security of VANETs is proposed, the distinctive feature of which is the early detection of malicious activity of network nodes. To achieve early detection of malicious activity, the parameters of VANETs are presented as a time series, after which their future values are predicted and anomalies are searched by using machine learning methods. The proposed approach makes it possible to improve the safety of intelligent transport systems 10.48612/jisp/grg8-p2zd-5gbt 004.056 information security VANET time series prediction attacks prevention https://jisp.spbstu.ru/article/2024.16.9/ 2024_2_rus.pdf

RAR RUS 104-116 0000-0002-0920-9009 The Ministry of Science and Education of the Republic of Azerbaijan Pashayev Fahrad Heydar pasha.farhad@gmail.com 0009-0002-4985-6371 Nakhchivan State Universty Zeynalov Javanshir Ibrahim 0009-0001-3136-6684 Nakhchivan University Najafov Hasan Taghi Creatıon of software technıcal tools to protect technologıcal processes from ınternet threats It is known that the rapid development of technological computer networks and SCADA systems has necessarily accelerated the process of integration between these networks and global Internet networks. As a result, the solution of many issues of technological and production processes has been simplified and opportunities have been created for remote control of the enterprise staff and operational staff. However, this situation has also created new threats previously non-existent to the above-mentioned monitoring, diagnostic and management systems. Targeted attacks are organized by specific specialized groups, hackers and, in some cases, government agencies on the Internet for specific industrial enterprises. Those who organize cyber attacks on technological process control systems, over time, improve their methods and tools, increase their professional level. They carefully study the objects they will attack and identify vulnerabilities in the software of the object management systems. Developed set of technical means is based on the application of STM32F4XX type controllers and LPT ports of computers. The article provides connection diagrams and assembly methods of technical means. These technical means and the exchange protocols created can act as a bridge between the global Internet and technological corporate computer networks. The article presents simple algorithms of protocols and working program fragments. Fragments of the program are given in the C programming language and in the DELPHI programming system. The developed software acts as a filter bridge between the global Internet and TKKŞ. Data exchange between these two networks is carried out by creating non-standard protocols using STM32F4XX controllers and LPT ports 10.48612/jisp/p79a-z1nu-71vk 004.3; 004.4 Internet attacks technological computer networks telemechanical systems malware random attacks STM32F4XX controller LPT port https://jisp.spbstu.ru/article/2024.16.10/ 2024_2_rus.pdf

RAR RUS 117-129 0009-0002-1075-6808 ITMO University Salihov fanny2man@gmail.com A model of a distributed storage system for private keys of crypto wallets With the development of Web3 technologies, the third generation of the Internet has become one of the most promising areas. It involves the use of decentralized, transparent and user-oriented applications. However, many Web3 projects do not pay due attention to security, which can lead to serious consequences. Even a small error in the code can make the system vulnerable, opening access to intruders. Because of this, the industry faces frequent security breaches that threaten users and undermine trust in new technologies. One of the main problems of Web3 is the management of private keys. This is a critical aspect of security, which is directly related to the protection of digital assets and personal information of users. The risk of loss or theft of the private key can lead to irreparable consequences, since in case of loss there is no way to restore or reset the key. This article discusses various ways to store the private key of a cryptographic wallet to ensure security. For example, a key can be divided into parts and stored encrypted on hardware media, or the whole encrypted key can be stored on secure media. Quantitative data were calculated using Shamir’s scheme 10.48612/jisp/z7u3-vp19-u74n 004.056.55 key management encryption secret sharing cryptography distributed storage system https://jisp.spbstu.ru/article/2024.16.11/ 2024_2_rus.pdf

RAR RUS 130-137 0009-0007-4911-8471 Research Institute «Kvant» Samarin Nikolay samarin_nik@mail.ru A method for finding errors in program code based on inmemory fuzzing The paper proposes a method of searching for errors in software based on “in-memory” code phasing. Within the framework of the method, special fragments called “points” are selected in the software code, and these “points” are subjected to phasing testing in isolation from the rest of the program code. A practical example of using the method is presented, as a result of which a memory corruption error was detected in the code 10.48612/jisp/39tp-t61k-29uv 004.056 information security software error detection mathematical modelling symbolic execution fuzzing https://jisp.spbstu.ru/article/2024.16.12/ 2024_2_rus.pdf

RAR RUS 138-151 0009-0002-8019-437X Altai State Technical University Teplyuk Pavel teplyukpavel@yandex.ru 0000-0001-5103-3177 Altai State Technical University Yakunin Aleksey almpas@list.ru Identifying security flaws in the Linux kernel using system call fuzzing The development of operating systems built on the basis of the Linux kernel contributes to the wider use of Linux distributions as the basis of system software in information systems for various purposes, incl. being objects of critical information infrastructure. The goal of the work is to analyze the available approaches and tools for fuzzing system calls of the Linux kernel, as well as experimental fuzzing testing of some current versions of the kernel, aimed at increasing the overall security of the Linux kernel. Theoretical analysis was used to evaluate and compare existing types of Linux kernel-level vulnerabilities, as well as approaches to kernel fuzzing. An empirical research method was also used, which involved identifying defects and vulnerabilities in a certain configuration of the Linux kernel using fuzzing testing Analyzed critical vulnerabilities at the kernel level, approaches to fuzzing, including system calls, and an experimental study was conducted using the syzkaller fuzzer, which identified defects and vulnerabilities in the Linux kernel versions 4.9 and 5.4, incl. memory use-after-free vulnerability. This area of research requires further development in order to detect new vulnerabilities in current kernel versions 10.48612/jisp/pdp9-d25r-g6eu 004.056 operating system kernel security threats vulnerabilities fuzzing attack surface syzkaller https://jisp.spbstu.ru/article/2024.16.13/ 2024_2_rus.pdf

RAR RUS 152-168 0000-0001-7126-6787 Peter the Great St. Petersburg Polytechnic University Zhemelev Georgiy wws.dev@gmail.com Automatic synthesis of 3D gas turbine blades shapes using machine learning The paper addresses the problem of 3D-representations and automatic synthesis of gas turbine blades shapes. First, we implemented a parametric method of descriptor-based representation using Bernstein polynomials and generalized it to produce controllable 3D-shapes. Then, we proposed a method of automatic synthesis of 3D-shapes based on the use of generative ML models for aerodynamic profiles. This method helps to reduce the number of geometric design variables used in the optimization of the aerodynamic shape of blades. Moreover, it enables automatic synthesis of 3D-shapes with representation independent of shapes level of detail. Its implementation is based on generative-adversarial network BezierGAN and makes it possible to produce arbitrary sized datasets of 3D blades having aerodynamic shapes. Finally, by interpreting and visualizing the generator’s latent space, we observed the subset of latent variables that has the most importance for rapid prototyping of gas turbine blades 10.48612/jisp/dx8x-2he5-tffd 004.89 gas turbine blade dataset 3D object representation machine learning generativeadversarial network Bezier curves Bernstein polynomials https://jisp.spbstu.ru/article/2024.16.14/ 2024_2_rus.pdf

RAR RUS 169-177 0009-0005-3102-5950 Peter the Great St. Petersburg Polytechnic University Izotova Oksana izotova@ibks.spbstu.ru 0000-0003-2849-4682 Peter the Great St. Petersburg Polytechnic University Lavrova Daria lavrova_ds@spbstu.ru

Russia, 195251, St. Petersburg, Polytechnicheskaya str., 29

Detection of artificially synthesized audio files using graph neural networks This paper describes a study of the problem of generalizing multimodal data in the detection of artificially synthesized audio files. As a solution to the stated problem, a method is proposed which combines simultaneous analysis of audio file characteristics with its semantic component presented in the form of text. The approach is based on graph neural networks and algorithmic approaches involving the analysis of keywords and text sentiment. The conducted experimental studies confirmed the validity and efficiency of the proposed approach 10.48612/jisp/p6rt-uvzz-b4k7 004.056 deepfake graph neural networks artificially synthesized audio file text analysis https://jisp.spbstu.ru/article/2024.16.15/ 2024_2_rus.pdf

RAR RUS 178-193 Peter the Great St. Petersburg Polytechnic University Tolgorenko Egor tolgorenko.em@edu.spbstu.ru Peter the Great St. Petersburg Polytechnic University Zubkov Evgeny zubkov.e@edu.spbstu.ru 0000-0002-2009-5460 Peter the Great St. Petersburg Polytechnic University Ovasapyan Tigran otd@ibks.spbstu.ru Authorship identification and verification using machine and deep learning methods The article presents research aimed at analyzing methods of text authorship identification and verification. The methods of transforming texts into vector representations and determining authorship through text classification are investigated. A dataset is formed, on which the investigated methods are tested, after which conclusions about their effectiveness are drawn. Further research directions are also proposed 10.48612/jisp/vhgh-3g1m-996v 004.056 authorship verification authorship identification classification deep learning methods machine learning N-gram TF-IDF PCA https://jisp.spbstu.ru/article/2024.16.16/ 2024_2_rus.pdf