Pub Date : 1900-01-01DOI: 10.21293/1818-0442-2021-24-4-46-51
I. Lubkin
The vulnerabilities using return-oriented programming pose threats to the functioning of information systems. There are many protection systems to counteract them. They are based on various principles of functioning. At the same time, there are no generally accepted approaches to assess the security of applied solutions. The paper proposes security metrics that allow obtaining objective data on the efficiency of protection against RoP vulnerabilities. Proposed security metrics show ability to perform attack by gain control over control flow graph.
{"title":"Application security metrics when using defense system against vulnerabilities based on return-oriented programming","authors":"I. Lubkin","doi":"10.21293/1818-0442-2021-24-4-46-51","DOIUrl":"https://doi.org/10.21293/1818-0442-2021-24-4-46-51","url":null,"abstract":"The vulnerabilities using return-oriented programming pose threats to the functioning of information systems. There are many protection systems to counteract them. They are based on various principles of functioning. At the same time, there are no generally accepted approaches to assess the security of applied solutions. The paper proposes security metrics that allow obtaining objective data on the efficiency of protection against RoP vulnerabilities. Proposed security metrics show ability to perform attack by gain control over control flow graph.","PeriodicalId":273068,"journal":{"name":"Proceedings of Tomsk State University of Control Systems and Radioelectronics","volume":"64 5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116260571","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1900-01-01DOI: 10.21293/1818-0442-2021-25-1-17-23
A. Movchan, E. Rogozhnikov, E. Dmitriev, S. Novichkov, D. Lakontsev
The paper presents a model for the propagation of a radio signal of a fifth-generation cellular communication system, taking into account the unevenness of the terrain. The aim of the study is to assess the signal power level on the receiving side of the fourth and fifth generation cellular communication system when the signal propagates over uneven terrain in the frequency bands FR1 (2.6 GHz), FR1 (4.9 GHz). When estimating the power of the radio signal on the receiving side in the model, the values of the height map of the of Tomsk city, obtained in the course of the SRTM3 program, were used as uneven terrain. The presented radio signal propagation model is the Longley Rice ITM (Irregular Terrain Model). For this model, the main expressions are given that determine the resulting signal attenuation, as well as expressions that describe the geometry of the propagation path. The article reflects the main factors that determine the propagation of centimeter waves characteristic of the fifth generation cellular communication system, presents the results of modeling the propagation of the fifth 5G and fourth 4G generation cellular signal using the example of various scenarios for the location of a subscriber terminal and a base station in the Tomsk city. The simulation was carried out for two frequency bands FR1 (4.9 GHz) of the 5G network and FR1 (2.6 GHz) of the 4G network. As a result of the simulation, the values of the attenuation of the signal power level during propagation along the given paths were obtained, and also, taking into account the parameters of the transceiver equipment, the values of the signal power on the receiving side were calculated. Based on the data obtained, a comparative assessment of the communication range for 4G and 5G systems was made.
{"title":"Calculation of signal attenuation of 5G cellular networks for frequencies of the FR1 band","authors":"A. Movchan, E. Rogozhnikov, E. Dmitriev, S. Novichkov, D. Lakontsev","doi":"10.21293/1818-0442-2021-25-1-17-23","DOIUrl":"https://doi.org/10.21293/1818-0442-2021-25-1-17-23","url":null,"abstract":"The paper presents a model for the propagation of a radio signal of a fifth-generation cellular communication system, taking into account the unevenness of the terrain. The aim of the study is to assess the signal power level on the receiving side of the fourth and fifth generation cellular communication system when the signal propagates over uneven terrain in the frequency bands FR1 (2.6 GHz), FR1 (4.9 GHz). When estimating the power of the radio signal on the receiving side in the model, the values of the height map of the of Tomsk city, obtained in the course of the SRTM3 program, were used as uneven terrain. The presented radio signal propagation model is the Longley Rice ITM (Irregular Terrain Model). For this model, the main expressions are given that determine the resulting signal attenuation, as well as expressions that describe the geometry of the propagation path. The article reflects the main factors that determine the propagation of centimeter waves characteristic of the fifth generation cellular communication system, presents the results of modeling the propagation of the fifth 5G and fourth 4G generation cellular signal using the example of various scenarios for the location of a subscriber terminal and a base station in the Tomsk city. The simulation was carried out for two frequency bands FR1 (4.9 GHz) of the 5G network and FR1 (2.6 GHz) of the 4G network. As a result of the simulation, the values of the attenuation of the signal power level during propagation along the given paths were obtained, and also, taking into account the parameters of the transceiver equipment, the values of the signal power on the receiving side were calculated. Based on the data obtained, a comparative assessment of the communication range for 4G and 5G systems was made.","PeriodicalId":273068,"journal":{"name":"Proceedings of Tomsk State University of Control Systems and Radioelectronics","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133291786","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1900-01-01DOI: 10.21293/1818-0442-2022-25-2-45-52
A. A. Sobolev, A. Fedotova, A. Kurtukova, A. Romanov, A. Shelupanov
The article describes the approaches to determining the age of the author of an anonymous text written in Russian. The fundamental works of the subject area are considered, both proven approaches (support vector machine, naive Bayes classifier, convolutional and recurrent neural networks) and modern methods (fastText, BERT) are implemented. The study used its own data set containing 1,5 million comments from social media users. A separate experiment is devoted to assessing the impact on the classification accuracy of various text vectorization methods. As a result of a series of experiments aimed at evaluating the efficiency of the methods used and selecting informative features, a model was obtained that can predict the age of the author of an anonymous text with an accuracy of 83.2%.
{"title":"Methodology to determine the age of the text’s author based on readability and lexical diversity metrics","authors":"A. A. Sobolev, A. Fedotova, A. Kurtukova, A. Romanov, A. Shelupanov","doi":"10.21293/1818-0442-2022-25-2-45-52","DOIUrl":"https://doi.org/10.21293/1818-0442-2022-25-2-45-52","url":null,"abstract":"The article describes the approaches to determining the age of the author of an anonymous text written in Russian. The fundamental works of the subject area are considered, both proven approaches (support vector machine, naive Bayes classifier, convolutional and recurrent neural networks) and modern methods (fastText, BERT) are implemented. The study used its own data set containing 1,5 million comments from social media users. A separate experiment is devoted to assessing the impact on the classification accuracy of various text vectorization methods. As a result of a series of experiments aimed at evaluating the efficiency of the methods used and selecting informative features, a model was obtained that can predict the age of the author of an anonymous text with an accuracy of 83.2%.","PeriodicalId":273068,"journal":{"name":"Proceedings of Tomsk State University of Control Systems and Radioelectronics","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124644964","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1900-01-01DOI: 10.21293/1818-0442-2021-25-1-79-85
A. Kurtukova, A. Romanov, A. Fedotova, A. Shelupanov
The article explores the approaches to determine the author of a natural language text, the advantages and disadvantages of these approaches. The identification is carried out using classical machine learning algorithms and neural network architectures (including fastText, CNN and LSTM and their hybrids, BERT). The efficiency of the model is evaluated based on the social media texts dataset. A separate experiment is devoted to the feature selection using a genetic algorithm. SVM trained on a selected 400 features set makes it possible to achieve up to 10% increase in accuracy for all considered numbers of authors. Neural networks achieve a classification accuracy of 96%, but their training time in some cases exceeds the time spent on training SVM and other classical machine learning methods in some cases. For SVM together with the genetic algorithm, the average accuracy was 66%, for deep neural networks and fastText – 73 and 68%, respectively.
{"title":"Application of machine learning methods and feature selection based on a genetic algorithm in solving the problem of determining the authorship of a Russian-language text for cybersecurity","authors":"A. Kurtukova, A. Romanov, A. Fedotova, A. Shelupanov","doi":"10.21293/1818-0442-2021-25-1-79-85","DOIUrl":"https://doi.org/10.21293/1818-0442-2021-25-1-79-85","url":null,"abstract":"The article explores the approaches to determine the author of a natural language text, the advantages and disadvantages of these approaches. The identification is carried out using classical machine learning algorithms and neural network architectures (including fastText, CNN and LSTM and their hybrids, BERT). The efficiency of the model is evaluated based on the social media texts dataset. A separate experiment is devoted to the feature selection using a genetic algorithm. SVM trained on a selected 400 features set makes it possible to achieve up to 10% increase in accuracy for all considered numbers of authors. Neural networks achieve a classification accuracy of 96%, but their training time in some cases exceeds the time spent on training SVM and other classical machine learning methods in some cases. For SVM together with the genetic algorithm, the average accuracy was 66%, for deep neural networks and fastText – 73 and 68%, respectively.","PeriodicalId":273068,"journal":{"name":"Proceedings of Tomsk State University of Control Systems and Radioelectronics","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124651820","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1900-01-01DOI: 10.21293/1818-0442-2021-24-4-19-24
I. A. Belova, M. V. Martinovich, D. Y. Fedorova
This work is devoted to the development of a combined source of artificial lighting to study the characteristics of solar cells. Spectral analysis of various radiation sources is performed. Based on the analysis, the necessary radiation sources are selected, which total spectrum, after approximation, is close to the spectrum of solar radiation. The calculation of electrooptical characteristics is carried out. The number of artificial lighting sources needed to reproduce the spectrum of solar radiation is calculated. The corresponding conclusions are made.
{"title":"Artificial light source simulating the solar spectrum for testing solar panels","authors":"I. A. Belova, M. V. Martinovich, D. Y. Fedorova","doi":"10.21293/1818-0442-2021-24-4-19-24","DOIUrl":"https://doi.org/10.21293/1818-0442-2021-24-4-19-24","url":null,"abstract":"This work is devoted to the development of a combined source of artificial lighting to study the characteristics of solar cells. Spectral analysis of various radiation sources is performed. Based on the analysis, the necessary radiation sources are selected, which total spectrum, after approximation, is close to the spectrum of solar radiation. The calculation of electrooptical characteristics is carried out. The number of artificial lighting sources needed to reproduce the spectrum of solar radiation is calculated. The corresponding conclusions are made.","PeriodicalId":273068,"journal":{"name":"Proceedings of Tomsk State University of Control Systems and Radioelectronics","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124862385","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1900-01-01DOI: 10.21293/1818-0442-2022-25-2-37-44
V. Tran, A. Korikov
Adaptive sliding control mode of an unmanned aerial vehicle (UAV) has been synthesized using neural networks to identify unknown factors acting on UAV. The MATLAB SIMULINK software was used to simulate the operation of the UAV control system. The simulation of the operation of the UAV location tracking system and UAV movement under the influence of unknown external forces of both constant magnitude and external forces varying according to a linear law is performed. An assessment of the performance of the UAV control system under the influence of random interference is given.
{"title":"Synthesis of adaptive sliding flight control mode of a quadrocopter under conditions of variable load and interference","authors":"V. Tran, A. Korikov","doi":"10.21293/1818-0442-2022-25-2-37-44","DOIUrl":"https://doi.org/10.21293/1818-0442-2022-25-2-37-44","url":null,"abstract":"Adaptive sliding control mode of an unmanned aerial vehicle (UAV) has been synthesized using neural networks to identify unknown factors acting on UAV. The MATLAB SIMULINK software was used to simulate the operation of the UAV control system. The simulation of the operation of the UAV location tracking system and UAV movement under the influence of unknown external forces of both constant magnitude and external forces varying according to a linear law is performed. An assessment of the performance of the UAV control system under the influence of random interference is given.","PeriodicalId":273068,"journal":{"name":"Proceedings of Tomsk State University of Control Systems and Radioelectronics","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124893501","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1900-01-01DOI: 10.21293/1818-0442-2019-22-1-7-66-70
E. Mishchenko, A. N. Sokolov
{"title":"Implementation algorithms for the methods of personal data depersonalization in distributed information systems","authors":"E. Mishchenko, A. N. Sokolov","doi":"10.21293/1818-0442-2019-22-1-7-66-70","DOIUrl":"https://doi.org/10.21293/1818-0442-2019-22-1-7-66-70","url":null,"abstract":"","PeriodicalId":273068,"journal":{"name":"Proceedings of Tomsk State University of Control Systems and Radioelectronics","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130475089","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1900-01-01DOI: 10.21293/1818-0442-2019-22-2-121-127
V. Rulevskiy, Radioeleсtronics
{"title":"Method to determine the optimal voltage and AC frequency in a three-phase cable-rope of the underwater power supply system","authors":"V. Rulevskiy, Radioeleсtronics","doi":"10.21293/1818-0442-2019-22-2-121-127","DOIUrl":"https://doi.org/10.21293/1818-0442-2019-22-2-121-127","url":null,"abstract":"","PeriodicalId":273068,"journal":{"name":"Proceedings of Tomsk State University of Control Systems and Radioelectronics","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129612701","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1900-01-01DOI: 10.21293/1818-0442-2023-26-1-65-75
K. Sarin
Online adaptation and interpretability have become one of the important requirements for machine learning models. Popular models such as artificial neural networks cannot fully implement them. Fuzzy classifiers of the Min-Max type are interpretable, thanks to the underlying fuzzy logic theory, and adaptable with the advent of new information. This article presents a comprehensive literature review on machine learning models based on fuzzy Min-Max classifiers. The architecture of the classifier and the principle of its operation are presented. A review of the modifications of the classifier is carried out and their effectiveness is evaluated. Applications of the classifier and its modifications in solving real problems are indicated. In conclusion, statements are drawn about the work of the classifier and the problems that have remained unresolved.
{"title":"Fuzzy Min-Max Сlassifier: Review","authors":"K. Sarin","doi":"10.21293/1818-0442-2023-26-1-65-75","DOIUrl":"https://doi.org/10.21293/1818-0442-2023-26-1-65-75","url":null,"abstract":"Online adaptation and interpretability have become one of the important requirements for machine learning models. Popular models such as artificial neural networks cannot fully implement them. Fuzzy classifiers of the Min-Max type are interpretable, thanks to the underlying fuzzy logic theory, and adaptable with the advent of new information. This article presents a comprehensive literature review on machine learning models based on fuzzy Min-Max classifiers. The architecture of the classifier and the principle of its operation are presented. A review of the modifications of the classifier is carried out and their effectiveness is evaluated. Applications of the classifier and its modifications in solving real problems are indicated. In conclusion, statements are drawn about the work of the classifier and the problems that have remained unresolved.","PeriodicalId":273068,"journal":{"name":"Proceedings of Tomsk State University of Control Systems and Radioelectronics","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127852461","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1900-01-01DOI: 10.21293/1818-0442-2019-22-3-43-48
D. Novokhrestova, E. Kostyuchenko, E. Kataeva, A. Buymov, D. N. Buintsev
{"title":"Software package for assessing speech intelligibility","authors":"D. Novokhrestova, E. Kostyuchenko, E. Kataeva, A. Buymov, D. N. Buintsev","doi":"10.21293/1818-0442-2019-22-3-43-48","DOIUrl":"https://doi.org/10.21293/1818-0442-2019-22-3-43-48","url":null,"abstract":"","PeriodicalId":273068,"journal":{"name":"Proceedings of Tomsk State University of Control Systems and Radioelectronics","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117052893","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：