Cybernetics And Systems Analysis logo
Editorial Board Announcements Abstracts Authors Archive
Cybernetics And Systems Analysis
International Theoretical Science Journal
-->

UDC 004.8, 519.7
O. Letychevskyi1


1 V.M. Glushkov Institute of Cybernetics of the NAS of Ukraine, Kyiv, Ukraine

oleksandr.letychevskyi@litsoft.com.ua

CONGNITIVE NETWORKS, THEIR PROPERTIES AND APPLICATIONS IN ATTACK
DETECTION AND PREVENTION SYSTEMS

Abstract. Methods of real-time cyberattack detection, based on an algebraic approach, are considered. The method of algebraic matching is used, which is based on the methods of solving behavioral equations and algebraic modeling. At the same time, to increase the efficiency of cyberattack detection and prevention, it is suggested to use the composition of a neural network for the classification of attacks and the method of algebraic matching. This construction is called a cognitive system, whose concept was first formulated in 2005. The properties of the cognitive network, such as double classification and self-learning, are considered, and the technological line for detecting cyberattacks using cognitive networks is presented.

Keywords: artificial intelligence, neuron network, deep machine learning, behaviour algebra, neuro-symbolic approach, algebraic modeling, insertion modelling.


full text

REFERENCES

  1. DARPA, “Cyber Grand Challenge.” URL: https://www.darpa.mil/program/cyber-grand-challenge .

  2. Mercaldo F., Martinelli F., Santone A. Real-time SCADA attack detection by means of formal methods. Proc. 2019 IEEE 28th International Conference on Enabling Technologies: Infrastructure for Collaborative Enterprises (WETICE) (12–14 June 2019, Napoli, Italy). Napoli, 2019. P. 231–236. https://doi.org/10.1109/WETICE.2019.00057.

  3. Kapitonova J., Letichevsky A. Algebraic programming in the APS system. Proc. ISSAC’90: Int’l Symposium on Symbolic Algebraic Computation (20–24 August 1990, Tokyo, Japan). Tokyo, 1990. P. 68–75. https://doi.org/10.1145/96877.96896.

  4. Gilbert D., Letichevsky A. A model for interaction of agents and environments. In: Recent Trends in Algebraic Development Techniques. Bert D., Choppy C. (Eds). LNCS. 1999. Vol. 1827. P. 311–328. https://doi.org/10.1007/978-3-540-44616-3_18.

  5. Letichevsky A., Letychevskyi O., Peschanenko V. Insertion modeling and its applications. Computer Science Journal of Moldova. 2016. Vol. 24, N 3. P. 357–370.

  6. Letichevsky A. Algebra of behavior transformations and its applications. In: Structural Theory of Automata, Semigroups, and Universal Algebra. NATO Science Series II. Mathematics, Physics and Chemistry. Kudryavtsev V.B., Rosenberg I.G. (Eds). Springer, 2005. Vol. 207. P. 241–272. https://doi.org/10.1007/1-4020-3817-8_10.

  7. Letychevskyi O., Peschanenko V. Applying algebraic virtual machine to cybersecurity tasks. 2022 IEEE 9th International Conference on Sciences of Electronics, Technologies of Information and Telecommunications (SETIT) (28–30 May 2022, Hammamet, Tunisia). Hammamet, 2022. P. 161–169. https://doi.org/10.1109/SETIT54465.2022.9875895.

  8. Letichevsky A., Letychevskyi O., Peschanenko V., Weigert T. Insertion modeling and symbolic verification of large systems. In: SDL 2015: Model-Driven Engineering for Smart Cities. Fischer J., Scheidgen M., Schieferdecker I., Reed R. (Eds). Lecture Notes in Computer Science. Cham: Springer International Publishing, 2015. Vol. 9369. P. 3–18. https://doi.org/10.1007/978-3-319-24912-4_1 .

  9. Thomas R.W., DaSilva L.A., MacKenzie A.B. Cognitive networks. Proc. First IEEE International Symposium on New Frontiers in Dynamic Spectrum Access Networks, 2005 (DySPAN 2005) (08–11 November 2005, Baltimore, MD, USA, 2005). Baltimore, 2005. P. 352–360. https://doi.org/10.1109/DYSPAN.2005.1542652.

  10. Hitzler P., Eberhart A., Ebrahimi M., Sarker M.K., Zhou L. Neuro-symbolic approaches in artificial intelligence. National Science Review. 2022. Vol. 9, Iss. 6. https://doi.org/10.1093/nsr/nwac035.




© 2023 Kibernetika.org. All rights reserved.