AUTOMATIC CONTROL AND COMPUTER SCIENCES最新文献

{"title":"On the Study of One Way to Detect Anomalous Program Execution","authors":"Y. V. Kosolapov,&nbsp;T. A. Pavlova","doi":"10.3103/S0146411625700257","DOIUrl":"10.3103/S0146411625700257","url":null,"abstract":"<p>Developing more accurate and adaptive methods for detecting malicious code is a critical challenge in the context of constantly evolving cybersecurity threats. This requires constant attention to new vulnerabilities and attack methods, as well as the search for innovative approaches to detecting and preventing cyber threats. This paper examines an algorithm for detecting the execution of malicious code in the process of a protected program. This algorithm is based on a previously proposed approach, when the legitimate execution of a protected program is described by a profile of differences in the return addresses of the called functions, also called a distance profile. A concept is introduced called positional distance, which is determined by the difference between the call numbers in the program trace. The main change was the ability to add to the profile the distances between the return addresses of not only neighboring functions but also several previous ones with the given positional distance. In addition to modifying the detection algorithm, this study develops a tool for automating the construction of a distance profile and experimentally studies the dependence of the probability of false detection of an atypical distance on the training duration for four well-known browsers. The experiments confirm that with a slight increase in verification time, the number of atypical distances detected by the proposed algorithm can be significantly lower than the number of atypical distances detected by the basic algorithm. However, it should be noted that the effect of the transition from the basic algorithm to the proposed one, as the results show, depends on the characteristics of the specific program being protected. The study highlights the importance of continually improving malware detection techniques to adapt them to changing threats and software operating conditions. As a result, this will ensure more reliable protection of information and systems from cyber attacks and other cyber threats.</p>","PeriodicalId":46238,"journal":{"name":"AUTOMATIC CONTROL AND COMPUTER SCIENCES","volume":"59 7","pages":"885 - 894"},"PeriodicalIF":0.5,"publicationDate":"2026-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147340621","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}

{"title":"Comparison of Pretrained Models for Domain-Specific Entity Extraction from Student Report Documents","authors":"A. V. Melnikova,&nbsp;M. S. Vorobeva,&nbsp;A. V. Glazkova","doi":"10.3103/S0146411625700439","DOIUrl":"10.3103/S0146411625700439","url":null,"abstract":"<p>The authors propose a methodology for extracting domain-specific entities (DSEs) from student report documents in the Russian language using pretrained transformer-based language models. Extracting DSEs from student report documents is a relevant task since the obtained data can be used for various purposes, ranging from the formation of project teams to the personalization of learning pathways. Additionally, automating the document processing workflow reduces the labor costs associated with manual processing. Expert-annotated student report documents are used as training material for training models. These documents were created by students in information technology programs between 2019 and 2022 for project-based and practical disciplines, as well as theses. The DSE extraction task is approached as two subtasks: named entity recognition (NER) and annotated text generation. A comparative analysis is conducted among NER encoder-only models (ruBERT, ruRoBERTa), encoder-decoder models (ruT5, mBART), and decoder-only models (ruGPT, T-lite) for text generation. The effectiveness of the models was evaluated using the F1-measure, together with an analysis of common errors. The highest F1-measure on the test set is achieved by mBART (93.55%). This model also shows the lowest error rate in DSE identification during text generation and annotation. The NER models demonstrated a lower tendency for errors but tended to extract DSEs in a fragmented manner. The obtained results indicate the applicability of the examined models for solving the stated tasks, considering the specific requirements of the problem.</p>","PeriodicalId":46238,"journal":{"name":"AUTOMATIC CONTROL AND COMPUTER SCIENCES","volume":"59 7","pages":"1170 - 1180"},"PeriodicalIF":0.5,"publicationDate":"2026-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147340169","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}

{"title":"Verification of Declarative LTL Specification of Control Program Behavior","authors":"M. V. Neyzov,&nbsp;E. V. Kuzmin","doi":"10.3103/S0146411625700233","DOIUrl":"10.3103/S0146411625700233","url":null,"abstract":"<p>This article continues the series of works on the development and verification of control programs based on LTL (linear temporal logic) specifications of a special type. Previously, a declarative LTL specification was proposed, which allows describing the behavior of control programs and building program code based on it in the imperative ST language for programmable logic controllers (PLCs). This LTL specification can be directly verified for compliance with specified temporal properties by the model checking method using the nuXmv symbolic verification tool. In general, it is not required to translate the LTL formulas of the specification into another formalism—an SMV specification (code in the input language of the nuXmv tool). The aim of this study is to explore alternative ways of representing the behavioral model of a program that conforms to a declarative LTL specification during its verification using the nuXmv tool. In this article, we transform the declarative LTL specification into various SMV specifications with accompanying changes of formulation of the verification problem, which leads to a significant reduction in time costs when checking temporal properties by using the nuXmv tool. The acceleration of verification is due to the reduction of the state space of the model being verified. The SMV specifications obtained as a result of the proposed transformations specify identical or bisimulational-equivalent transition systems, ensuring the same verification results when replacing one SMV specification with another.</p>","PeriodicalId":46238,"journal":{"name":"AUTOMATIC CONTROL AND COMPUTER SCIENCES","volume":"59 7","pages":"859 - 876"},"PeriodicalIF":0.5,"publicationDate":"2026-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147340296","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}

{"title":"Extremal Estimates of the Wiener Index for Weakly Connected Directed Graphs","authors":"D. Y. Chalyy","doi":"10.3103/S0146411625700403","DOIUrl":"10.3103/S0146411625700403","url":null,"abstract":"<p>This article considers the Wiener index for weakly connected directed graphs. For such graphs, the distance <span>(d(u,v))</span> between vertices <span>(u)</span> and <span>(v)</span> is not always defined, which requires a correction for the Wiener index to be meaningful. The convention where it is assumed that <span>(d(u,v) = 0)</span> in the absence of a path between vertices is well-studied. We consider the convention where <span>(d(u,v))</span> is equal to the number of vertices in the graph when there is no path between vertices <span>(u)</span> and <span>(v)</span>. This article presents graphs with <span>(n)</span> vertices for which the Wiener index with this convention reaches the minimal and maximal values. We also present experimental results showing how the Wiener index (considering both conventions of distance) changes when arcs are added to a weakly connected directed graph with fixed and random structures.</p>","PeriodicalId":46238,"journal":{"name":"AUTOMATIC CONTROL AND COMPUTER SCIENCES","volume":"59 7","pages":"1132 - 1143"},"PeriodicalIF":0.5,"publicationDate":"2026-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147340597","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}

{"title":"Hierarchical Classification of Scientific Articles Using Deep Learning (Using the UDC Hierarchy As an Example)","authors":"V. Y. Mamedov,&nbsp;D. A. Kovalevsky,&nbsp;D. A. Morozov,&nbsp;S. S. Stolyarov,&nbsp;S. S. Ospichev","doi":"10.3103/S0146411625700440","DOIUrl":"10.3103/S0146411625700440","url":null,"abstract":"<p>The exponential growth of scientific publications has heightened the need for robust tools to organize and retrieve research effectively. The Universal Decimal Classification (UDC) serves as a valuable framework for categorizing articles by subject area. However, manual assignment of UDC codes is often prone to inaccuracies or oversimplification, limiting its utility. In this study, we present a novel approach for the automated assignment of UDC codes to scientific articles using BERT-based models. Our methodology is trained and evaluated on a dataset comprising over 19 000 articles in mathematics and related disciplines. To address the hierarchical structure of the UDC, we develop two specialized evaluation metrics: hierarchical classification accuracy and hierarchical recommendation accuracy. We also explore multiple strategies for flattening hierarchical labels. Our results demonstrate a hierarchical recommendation accuracy of 0.8220. Furthermore, blind expert evaluation reveals that discrepancies between the reference and predicted labels often stem from errors in the original UDC code assignments by the authors of articles. Our approach demonstrates strong potential for automating the classification of scientific articles and can be extended to other hierarchical classification systems.</p>","PeriodicalId":46238,"journal":{"name":"AUTOMATIC CONTROL AND COMPUTER SCIENCES","volume":"59 7","pages":"1181 - 1192"},"PeriodicalIF":0.5,"publicationDate":"2026-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147340618","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}

{"title":"Methods for Sentiment Detection toward Aspects of Economic and Social Development in Russian Sentences","authors":"A. Y. Poletaev,&nbsp;I. V. Paramonov,&nbsp;E. I. Boychuk","doi":"10.3103/S014641162570035X","DOIUrl":"10.3103/S014641162570035X","url":null,"abstract":"<p>This article studies the task of sentiment detection toward aspects of economic and social development in Russian sentences. The aspect toward which the sentiment is determined can be either explicitly mentioned or implied. The authors study the possibilities of using neural network classifiers and propose an algorithm for determining the sentiment toward an aspect based on semantic rules implemented with the use of constituency trees. The sentiment toward an aspect is determined in two stages. At the first stage, aspect terms (explicitly mentioned events or phenomena associated with the aspect) are found in the sentence. At the second stage, the sentiment toward an aspect is calculated as the sentiment toward the aspect term that is most closely associated with the aspect. This paper proposes several methods for searching the aspect terms. The model’s performance is assessed on a corpus of 468 sentences extracted from election campaign materials. The best result for neural network classifiers is obtained using the BERT-SPC neural network pretrained on the task of identifying the sentiment toward an explicitly mentioned aspect; the macro F-measure is 0.74. The best result for the semantic rule-based algorithm is obtained using the method of aspect term searching based on semantic similarity; the macro-F-measure is 0.63. When combining BERT-SPC and the rule-based algorithm into an ensemble, the macro-F-measure is 0.79, which is the best result obtained in this study.</p>","PeriodicalId":46238,"journal":{"name":"AUTOMATIC CONTROL AND COMPUTER SCIENCES","volume":"59 7","pages":"1032 - 1047"},"PeriodicalIF":0.5,"publicationDate":"2026-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147340620","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}

{"title":"Suppression of Additive Periodic Low-Frequency Interference on Eddy-Current Defectograms","authors":"L. Y. Bystrov,&nbsp;A. N. Gladkov,&nbsp;E. V. Kuzmin","doi":"10.3103/S0146411625700269","DOIUrl":"10.3103/S0146411625700269","url":null,"abstract":"<p>Traffic safety in railway transport requires regular inspection of the condition of rails to identify and timely eliminate defects. Eddy-current flaw detection is one of the popular methods of nondestructive rail testing. The data (defectograms) obtained from eddy-current flaw detectors during rail testing are typically high-volume and therefore require efficient automated analysis. In this context, analysis means the process of detecting the presence of defective areas on defectograms, as well as identifying the structural elements of the rail track, taking into account noise and various types of interference. The threshold noise level is found to isolate signals from defects and structural elements. Its value can be distorted by electromagnetic influences superimposed on the signals, which have pronounced low frequency and periodicity. This interference raises the threshold noise level, complicating the detection of useful signals. In relation to this, these types of effects need to be suppressed. In this paper spectral subtraction is used as a method for interference reduction in eddy-current defectograms. The interference function is defined as the sum of the low-frequency harmonics of the discrete Fourier transform of the original signals. Then the cleaned signal can be found by subtracting the low-frequency range. The upper boundary of this range is referred to as the threshold harmonic frequency. This frequency is determined by minimizing the distance of the signal’s autocorrelation function and expected autocorrelation. Two types of expected correlation are proposed: Gaussian noise autocorrelation and the reference autocorrelation. Both approaches allow us to determine the threshold harmonic frequency at which periodic interference is most effectively suppressed. The method based on Gaussian noise autocorrelation method is, to some extent, universal for eddy-current defectograms, while the reference autocorrelation is data- and recording equipment-specific. The most suitable threshold harmonic frequency is found for the eddy-current defectogram data under consideration. The described approaches to suppressing periodic low-frequency interference may also be successfully applied in other fields beyond eddy-current testing.</p>","PeriodicalId":46238,"journal":{"name":"AUTOMATIC CONTROL AND COMPUTER SCIENCES","volume":"59 7","pages":"895 - 909"},"PeriodicalIF":0.5,"publicationDate":"2026-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147340297","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}

{"title":"Pattern-Based Approach to the Automation of Deductive Verification of Process-Oriented Programs: Patterns, Lemmas, and Algorithms","authors":"I. M. Chernenko,&nbsp;I. S. Anureev","doi":"10.3103/S0146411625700361","DOIUrl":"10.3103/S0146411625700361","url":null,"abstract":"<p>Process-oriented programming is an approach to developing control software in which a program is defined as a set of interacting processes. PoST is a process-oriented language, which is an extension of the ST language from the IEC 61131-3 standard. In the field of control software development, formal verification plays an important role due to the need to ensure high reliability of such software. Deductive verification is a formal verification method in which a program and its requirements are represented as logical formulas, and logical inference is used to prove that the program satisfies the requirements. Control software often has temporal requirements. We formalize such requirements for process-oriented programs as control loop invariants. However, control loop invariants that represent requirements are not sufficient to prove the correctness of the program. Therefore, we add extra invariants containing auxiliary information. This paper considers the problem of automating deductive verification of process-oriented programs. An approach is proposed in which temporal requirements are specified using requirement patterns which are constructed from basic patterns. For each requirement pattern, a corresponding extra invariant pattern and lemmas are defined. In this paper, the proposed approach and schemes of basic and derived requirement patterns are described. The schemes of basic extra invariant patterns, schemes of lemmas defined for basic patterns, and a set of basic patterns and lemmas for them are considered. The scheme of derived extra invariant patterns and schemes of lemmas defined for derived patterns are defined. The algorithms for constructing derived extra invariant patterns and lemmas for them, as well as methods for proving these lemmas are presented. The schemes of proving verification conditions are considered. The proposed approach is demonstrated with an example. The analysis of related works has also been carried out.</p>","PeriodicalId":46238,"journal":{"name":"AUTOMATIC CONTROL AND COMPUTER SCIENCES","volume":"59 7","pages":"1048 - 1081"},"PeriodicalIF":0.5,"publicationDate":"2026-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147340614","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}

{"title":"UAV Detection Using Neural Networks","authors":"M. D. Averina,&nbsp;O. A. Levanova,&nbsp;D. V. Grushevskaya,&nbsp;K. A. Kukharev,&nbsp;D. M. Murin,&nbsp;M. A. Kalinin","doi":"10.3103/S0146411625700270","DOIUrl":"10.3103/S0146411625700270","url":null,"abstract":"<p>The availability of unmanned aerial vehicles (UAVs) has led to a significant increase in the number of offenses involving their use. This makes the development of UAV detection systems relevant. Solutions based on deep neural networks show the best results in detecting UAVs on video. This article presents a study of various neural network detectors and focuses on identifying objects as small as possible, up to <span>(4 times 4)</span> and even <span>(3 times 3)</span> pixels. This paper studies SSD (VGG16) and YOLOv3 architectures and their modifications. Precision and recall metrics are calculated separately for different intervals of the object areas. The best result is obtained for the YOLOv3 model with the bbox parameter values selected through the clustering of object sizes. Small (<span>(3 times 3)</span> px) drones are successfully identified with 76% precision and a very small recall of 26%. For objects between 10 and 20 pixels in area, the recall is 64% with precision of 75%. For objects with an area more than 20px the recall is about 90%, the precision is 89%, and the F1-measure is 90%. These results show that it is possible to recognize even <span>(4 times 4)</span> pixel drones, which can be used in video surveillance systems.</p>","PeriodicalId":46238,"journal":{"name":"AUTOMATIC CONTROL AND COMPUTER SCIENCES","volume":"59 7","pages":"910 - 919"},"PeriodicalIF":0.5,"publicationDate":"2026-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147340615","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}

{"title":"Algorithm for Constructing the Asymptotics of Periodic Solutions in Laser Models with a Rapidly Oscillating Delay","authors":"E. V. Grigorieva,&nbsp;D. V. Glazkov,&nbsp;A. O. Tolbey","doi":"10.3103/S0146411625700397","DOIUrl":"10.3103/S0146411625700397","url":null,"abstract":"<p>The problem of the stability of the equilibrium state in a laser system with fast oscillating coefficients is considered. A system averaged over fast oscillations and with a distributed delay is constructed. Critical cases in the problem of the stability of the equilibrium state are singled out. It is shown that the threshold value of the feedback coefficient at which the equilibrium state becomes unstable increases due to rapid oscillations compared to the corresponding value in the absence of modulation. In critical cases, normal forms are constructed—equations for the slowly varying amplitude of the periodic solutions. The conditions for the existence, stability, and instability of cycles are revealed.</p>","PeriodicalId":46238,"journal":{"name":"AUTOMATIC CONTROL AND COMPUTER SCIENCES","volume":"59 7","pages":"1125 - 1131"},"PeriodicalIF":0.5,"publicationDate":"2026-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147340616","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}