REGULARITIES OF CYBERATRACKS IN EU COUNTRIES USING ASSOCIATION RULES

O. Kuzmenko

Sumy State University,
Sumy, Ukraine

T. Dotsenko

Sumy State University,
Sumy, Ukraine

V. Bozhenko

Sumy State University,
Sumy, Ukraine

A. Svitlychna

Sumy State University,
Sumy, Ukraine

Pages: 95-103

Original language: Ukrainian

DOI: 10.21272/1817-9215.2021.1-11

Summary:

The transition to public information, the proliferation of e-commerce and the inadequate level of digital literacy have led to an increase in cyber fraud, which requires the improvement of existing and the development of new methods and ways to protect information infrastructure. The purpose of this study is to determine the patterns of cyberattacks in the European Union by using association rules. Authors have used such methods as: logical generalization – make database of cyberattacks, which includes the year, countries-victims, countries-sponsors, type and category of fraud; Data Mining - Association Rules modeling; visualization and graphic design - when make a network of associative rules of causal relationships between the studied phenomena of cyberattacks. This innovative technology to analyze data allows to identify relationships and patterns between related events or elements. The study found that in 77.14% of cases, espionage is carried out by criminals from Russia, in 88.24% - from Germany, in 93.75% - from China. 84.62% of espionage is observed in the private sector, 82.05% - in the public sector. The share of observations for which espionage is carried out from Russia is 43.55%. The share of observations for which espionage is carried out from both Germany and China is 24.19% of the sample. The largest share of observations (51.61%) corresponds to cyberattacks in the form of espionage in the public sector, and 35.48% of observations correspond to the private sector. In 76% of cases, espionage is carried out by criminals from Russia. The developed technique will allow quickly and automatically process a significant amount of input information, identify the most complete, most informative set of patterns, determine the risk of cyber fraud on the basis of European countries, to make effective decisions to manage such risk, minimize it, with the least resources. anticipation of cyber threats, counteraction to cyber attacks in the EU countries. The obtained results will be of practical value for public authorities and international organizations for the current analysis and adoption of a set of preventive measures to combat cyberthreats.

Keywords:
cyberattacks, cybercrimes, EU countries, modeling, associative rules.

Reference:
  1. Rehman, S. U., Khaliq, M., Imtiaz, S. I., Rasool, A., Shafiq, M., Javed, A. R., Bashir, A. K. (2021). DIDDOS: An approach for detection and identification of distributed denial of service (DDoS) cyberattacks using gated recurrent units (GRU).Future Generation Computer Systems, 118, 453-466. doi:10.1016/j.future.2021.01.022.
  2. Kamiya, S., Kang, J., Kim, J., Milidonis, A., & Stulz, R. M. (2021). Risk management, firm reputation, and the impact of successful cyberattacks on target firms.Journal of Financial Economics, 139(3), 719-749. doi:10.1016/j.jfineco.2019.05.019.
  3. Moazeni, F., & Khazaei, J. (2021). Sequential false data injection cyberattacks in water distribution systems targeting storage tanks; a bi-level optimization model.Sustainable Cities and Society, 70 doi:10.1016/j.scs.2021.102895.
  4. Mercader P., Haddad J. (2021). Resilient multivariable perimeter control of urban road networks under cyberattacks. Control Engineering Practice, 109 doi:10.1016/j.conengprac.2020.104718.
  5. Petrillo, A., Pescape, A., & Santini, S. (2021). A secure adaptive control for cooperative driving of autonomous connected vehicles in the presence of heterogeneous communication delays and cyberattacks.IEEE Transactions on Cybernetics, 51(3), 1134-1149. doi:10.1109/TCYB.2019.2962601.
  6. Palmieri, M., Shortland, N., & McGarry, P. (2021). Personality and online deviance: The role of reinforcement sensitivity theory in cybercrime.Computers in Human Behavior, 120. doi:10.1016/j.chb.2021.106745.
  7. Govender, I., Watson, B. W. W., & Amra, J. (2021). Global virus lockdown and cybercrime rate trends: A routine activity approach. Journal of Physics: Conference Series, 1828(1). doi:10.1088/1742-6596/1828/1/012107
  8. De Kimpe, L., Walrave, M., Verdegem, P., & Ponnet, K. (2021). What we think we know about cybersecurity: An investigation of the relationship between perceived knowledge, internet trust, and protection motivation in a cybercrime context. Behaviour and Information Technology. doi:10.1080/0144929X.2021.1905066.
  9. Lyeonov, S., Żurakowska-Sawa, J., Kuzmenko, O., & Koibichuk, V. (2020). Gravitational and intellectual data analysis to assess the money laundering risk of financial institutions.Journal of International Studies, 13(4), 259-272. doi:10.14254/2071-8330.2020/13-4/18.
  10. Leonov, S., Yarovenko, H., Boiko, A., & Dotsenko, T. (2019). Information system for monitoring banking transactions related to money laundering. CEUR Workshop Proceedings, 2422, 297-307.
  11. Kuzmenko, O., Vasylieva, T., Vojtovič, S., Chygryn, O., & Snieška, V. (2020). Why do regions differ in vulnerability to сovid-19? spatial nonlinear modeling of social and economic patterns.Economics and Sociology, 13(4), 318-340. doi:10.14254/2071-789X.2020/13-4/20.
  12. Horban, H., Kandyba, I., Dvoretskyi, M., & Boiko, A. (2021). Principles of searching for a variety of types of associative rules in OLAP-cubes. CEUR Workshop Proceedings, 2845,181-192.
  13. Savchuk, T. O., Pryimak, N. V., Slyusarenko, N. V., Smolarz, A., Smailova, S., & Amirgaliyev, Y. (2020). Improved method of searching the associative rules while developing the software. International Journal of Electronics and Telecommunications, 66(3), 425-430. doi:10.24425-ijet.2020.131895/715.
  14. Bova, V., Shcheglov, S., & Leshchanov, D. (2019). Modified approach to problems of associative rules processing based on genetic search. Proceedings - 2019 International Russian Automation Conference, RusAutoCon 2019, doi:10.1109/RUSAUTOCON.2019.8867675
  15. Malaterre, C., Chartier, J., & Lareau, F. (2020). The recipes of philosophy of science: Characterizing the semantic structure of corpora by means of topic associative rules.PLoS ONE, 15. doi:10.1371/journal.pone.0242353.
  16. Hachaj, T., & Miazga, J. (2020). Image hashtag recommendations using a voting deep neural network and associative rules mining approach. Entropy, 22(12), 1-13. doi:10.3390/e22121351.