ANALYSIS OF THE PROBLEM OF MULTIVALUED OF CLASS LABELS ON THE SECURITY OF COMPUTER NETWORKS

D. I. Rakovskiy,
Moscow Technical University of Communications and Informatics (MTUCI), Moscow, Russia, Prophet_alpha@mail.ru

DOI: 10.36724/2664-066X-2022-8-6-10-17

SYNCHROINFO JOURNAL. Volume 8, Number 6 (2022). P. 10-17.

Abstract

Modern computer networks have a complex infrastructure that requires constant monitoring to detect anomalous conditions that can cause malfunctions, which is unacceptable for large-scale distributed networks. An important problem in the intelligent processing of syslog data is the existence of multilabel datasets. Among the Russian language scientific publications, the problem under consideration in the context of information security of computer networks is not presented. The purpose of the research work is to increase the security of computer networks through the use of multi-label learning methods in solving the problem of classifying system log class labels. In this paper, a comparative analysis of single-label and multi-label classifiers in a computational experiment on the Mean accuracy metric was carried out. According to the results of the analysis, 80% of single-label classifiers were inferior in classification accuracy according to the Mean accuracy multi-label metric to their counterparts, which may indicate a strong influence of multi-label class labels on the models under consideration. The considered structure of experimental data in a tabular form is influenced by the multi-label problem much more strongly than it can be estimated by a standard frequency check, which actualizes further research in this direction.

Keywords: supervised learning, multi-label classification, multiclass classification, information security, multi-label learning

References

1. A. Kuznetsov, V. Babenko, K. Kuznetsova, S. Kavun, O. Smirnov, O. Nakisko “Malware correlation monitoring in computer networks of promising smart grids”, Proceedings of the IEEE 6th International Conference on Energy Smart Systems, ESS 2019, 2019, pp. 347-352. DOI: 10.1109/ESS.2019.8764228
2. A.S. Bol’shakov, D.I. Rakovskii “An efficient multiple-criteria decision analysismethod in the field of information security”, Legal Informatics, 2020, no 4. pp. 55-66. DOI 10.21681/1994-1404-2020-4-55-66.
3. I.V. Kotenko, S.S.  Khmyrov “Analysis of models and techniques used for attribution of cyber security violators in the implementation of targeted attacks”, Voprosy kiberbezopasnosti, 2022, vol 50, no 4, pp. 52-79. DOI 10.21681/2311-3456-2022-4-52-79.
4. D.A. Gaifulina, I.V.  Kotenko “Application of deep learning methods in cybersecurity tasks”, Voprosy kiberbezopasnosti, 2020, vol 37, no 3. pp. 76-86. DOI 10.21681/2311-3456-2020-03-76-86.
5. M. Alrammal, M. Naveed, S. Rihawi “Using heuristic approach to build anti-malware”, Proceedings of the ITT 2018 – Information Technology Trends: Emerging Technologies for Artificial Intelligence. 5, Emerging Technologies for Artificial Intelligence, 2019, pp. 191-196. DOI: 10.1109/CTIT.2018.8649499.
6. A.S. Bol’shakov, D.I. Rakovskii “Software for modelling information security threats in information systems”, Pravovaya informatika, 2020, no 1, pp. 26—39. DOI: 10.21681/1994-1404-2020-1-26-39. E.Y. Pavlenko, N.V. Gololobov, D.S. Lavrova, A.V.  “Kozachok Recognition of cyber threats on the adaptive network topology of large-scale systems based on a recurrent neural network”, Voprosy kiberbezopasnosti, 2022, vol. 52, no 6, pp. 93 – 98. DOI:10.21681/2311-3456-2022-6-93-99
7. K.E. Izrailov, M.V. Buinevich, I.V. Kotenko, V.A. “Desnitsky Assessment and prediction of the complex objectsstate: applicatioin for information security”, Voprosy kiberbezopasnosti, 2022, vol 52, no 6, pp. 2 – 21. DOI:10.21681/23113456-6-2022-2-21
8. O.I. Sheluhin, A.V. Osin, D.I. Rakovsky “New Algorithm for Predicting the States of a Computer Network Using Multivalued Dependencies”, Automatic Control and Computer Sciences, 2023, vol. 57, no 1, pp. 48–60. DOI: 10.3103/S0146411623010091
9. E. Gibaja, S. Ventura “A Tutorial on Multi-Label Learning”, ACM Computing surveys, 2015, no 47, pp. 1-40. DOI: 10.1145/2716262
10. A.C.E.S. Lima, L.N. de Castro “A multi-label, semi-supervised classification approach applied to personality prediction in social media”, Neural Networks, 2014, vol. 58, pp. 122-130.
11. S.N. Karpovich “Multi-Label Classification of Text Documents using Probabilistic Topic Model ml-PLSI”, Trudy SPIIRAN, 2016, vol 47, no 4, pp. 92-104 DOI: 10.15622/sp.47.5
12. I.V. Kotenko, I.B. Saenko, A.A. Branitsky, I.B. Paraschuk, D.A. Gayfulina “Intelligent system of analytical processing of digital network content for its protection from unwanted information”, Informatics and automation, 2021, vol. 20, no 4, pp. 755-784
13. G.G. Kulikov, V.V. Antonov, Antonov D.V. “Analysis of the possibility of analytical knowledge extraction of a formal model of subject domain information system by neural network methods”, Neurocomputers, 2013, no 3, pp. 12-16. 
14. M. Azad, M. Moshkov “A Bi-criteria Optimization Model for Adjusting the Decision Tree Parameters”, Kuwait Journal of Science, 2022, vol. 49, no 2, pp. 1–14. DOI 10.48129/kjs.10725
15. A. Niemistö , O. Yli-Harja, I. Shmulevich, V.V. Lukin, A.N. Dolia “Correction of misclassifications using a proximity-based estimation method”, Eurasip Journal on Applied Signal Processing, vol. 2004, no 8, pp. 1142-1155. DOI: 10.1155/S1110865704402145
16. A.S. Markov “Cybersecurity and information security as nomenclature bifurcation scientific specialties (Russian text)”, Voprosy kiberbezopasnosti, 2022, vol 47, no 1, pp. 2-9. DOI 10.21681/2311-3456-2022-1-2-9
17. Lovtsov D. “Principles of ensuring information security in ergasystems”, Legal Informatics, 2021, no 1, pp. 36-50. DOI 10.21681/1994-1404-2021-1-36-50
18. A. S. Bolshakov, R. V. Khusainov, A.V. Osin “Traffic anomaly detection using a neural network to ensure information protection”, I-methods, 2021, vol. 13, no 4, pp. 1 – 15.
19. O.I. Sheluhin, D.I. Rakovskiy “Prediction of the profile functioning of a computer system (network) based on multivalued patterns”, Voprosy kiberbezopasnosti, 2022, no 6, pp. 28-45 (in Russian) DOI:10.21681/2311-3456-2022-6-53-70
20. O.I. Sheluhin, D.I. Rakovsky “Selection of metric and categorical attributes of rare anomalous events in a computer system using data mining methods”, T-Comm. 2021, vol. 15, no. 6, pр. 40-47. (in Russian) DOI: 10.36724/2072-8735-2021-15-6-40-47
21. B. Raja, K. Ravindranath, B. “Jayanag Monitoring and analysing anomaly activities in a network using packetbeat”, International Journal of Innovative Technology and Exploring Engineering, 2019, Vol. 8, No 6, Pp. 45-49.
22. I.V. Kotenko, A.A. Kuleshov, I.A. Ushakova “System for collecting, storing and processingsecurity information and events based on elasticstack tools”, Informatics and Automation (SPIIRAS Proceedings), 2017, vol. 54, no 5, pp. 5-34. DOI 10.15622/sp.54.1(in Russian)
23. V.V. Petrov, K.V. Bryukhanov, E.Y. Avksentieva “Network monitoring: network traffic analysis using ELK”, In Modern Science: actual problems of theory & practice, 2020, no 5, pp. 102-105. DOI 10.37882/2223-2966.2020.05.34. (in Russian)
24. G. Calderon, G. Del Campo, E. Saavedra, A. Santamaria “Management and Monitoring IoT Networks through an Elastic Stack-based Platform”, Proceedings of 2021 International Conference on Future Internet of Things and Cloud, FiCloud 2021. Virtual, Online, 2021, Pp. 184-191. DOI 10.1109/FiCloud49777.2021.00034.
25. I.V. Kotenko, A.A. Kuleshov, I.A. Ushakov “Aggregation of elastic stack instruments for collecting, storing and processing of security information and events”, Proceedings of the 2017 IEEE SmartWorld, Ubiquitous Intelligence & Computing, Advanced & Trusted Computed, Scalable Computing & Communications, Cloud & Big Data Computing, Internet of People and Smart City Innovation (SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI). California, USA: Institute of Electrical and Electronics Engineers, 2017, pp. 1 – 8. DOI 10.1109/UIC-ATC.2017.8397627.
26. U. Chaudhuri, S. Dey, B. Banerjee, A. Bhattacharya, M. Datcu “Interband Retrieval and Classification Using the Multilabeled”, Sentinel-2 BigEarthNet Archive. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2021, vol. 14, pp. 9884-9898. DOI 10.1109/JSTARS.2021.3112209
27. L. Maltoudoglou, A. Paisios, H. Papadopoulos, L. Lenc, J. Martínek, P. Král “Well-calibrated confidence measures for multi-label text classification with a large number of labels”, Pattern Recognition, 2022, vol. 122, pp. 108271. DOI: 10.1016/j.patcog.2021.108271
28. O.I. Sheluhin, S.Yu. Rybakov, A.V. Vanyushina “Modified Algorithm for Detecting Network Attacks Using the Fractal Dimension Jump Estimation Method in Online Mode”, Proceedings of Telecommunication Universities, 2022, vol. 8, no 3, pp. 117-126. (in Russian) https://doi.org/10.31854/1813-324X-2022-8-3-117-126