THE ROLE OF CYBERSECURITY IN FACILITATING DIGITAL ECONOMY: A TREE PARITY MACHINE-BASED APPROACH
DOI:
https://doi.org/10.20535/2411-2976.22025.36-47Keywords:
Tree Parity Machine (TPM), post-quantum cryptography, secure key exchange, IoT security, neural synchronisation, cyber-attack preventionAbstract
Background. As the digital economy expands, ensuring secure communication and data integrity becomes increasingly vital. Traditional cryptographic algorithms such as RSA and ECC are vulnerable to quantum computing advances, necessitating post-quantum solutions. Tree Parity Machines (TPMs), inspired by neural synchronisation principles, present a promising alternative for secure key exchange, particularly within Internet of Things (IoT) environments.
Objective. This study aims to evaluate the effectiveness of TPMs as a lightweight, energy-efficient, and quantum-resistant method for secure key generation and exchange in cybersecurity applications, with a focus on IoT networks.
Methods. A hybrid methodology combining theoretical analysis and practical simulations was employed. Theoretical modelling explored TPM synchronisation mechanisms, key generation dynamics, and resilience to cyber-attacks such as man-in-the-middle, replay, brute force, and eavesdropping. Practical simulations were conducted in a controlled network environment to assess TPM performance in terms of synchronisation time, key generation rate, computational overhead, and resistance to attacks, compared with traditional cryptographic methods.
Results. Simulation results demonstrated that TPMs outperform RSA/ECC across multiple parameters. TPMs achieved a synchronisation time of 15.2 ms versus 45.6 ms for RSA/ECC, a key generation rate of 500 keys/s compared to 120 keys/s, and reduced energy consumption (1.2 mJ vs. 3.8 mJ). They also exhibited superior resistance to man-in-the-middle attacks (99.9% vs. 90.4%) and required less computational overhead. These findings confirm TPMs’ robustness, scalability, and suitability for resource-constrained IoT environments.
Conclusions. Tree Parity Machines provide an efficient, post-quantum-secure alternative to conventional cryptography, offering enhanced protection against emerging cyber threats. Their lightweight architecture, rapid synchronisation, and minimal energy consumption position them as a key enabler of secure digital infrastructure. Future research should explore TPM integration with blockchain, federated learning, and edge computing to further strengthen cybersecurity frameworks.
References
M. Stypiński and M. Niemiec, “Synchronization of Tree Parity Machines Using Nonbinary Input Vectors,” IEEE Transactions on Neural Networks and Learning Systems, pp. 1–7, 2022.
M. Stypiński and M. Niemiec, “Security of Neural Network-Based Key Agreement Protocol for Smart Grids,” Energies, vol. 16, no. 10, 2023.
E. Shishniashvili, L. Mamisashvili, and L. Mirtskhulava, Enhancing IoT Security Using Multi-Layer Feedforward Neural Network with Tree Parity Machine Elements, Tbilisi: [Publisher Name], 2022.
L. Mirtskhulava, N. Gulua, and N. Meshveliani, “IoT Security Analysis Using Neural Key Exchange,” GESJ: Computer Science and Telecommunications, no. 2(57), 2019.
É. Salguero Dorokhin, W. Fuertes, and E. Lascano, “On the Development of an Optimal Structure of Tree Parity Machine for the Establishment of a Cryptographic Key,” Security and Communication Networks, vol. 2019, pp. 1–10, 2019.
A. Sarkar, J. Dey, and A. Bhowmik, “Multilayer Neural Network Synchronized Secured Session Key Based Encryption in Wireless Communication,” Indonesian Journal of Electrical Engineering and Computer Science, vol. 14, no. 1, pp. 169–176, 2019.
M. Niemiec, “Error Correction in Quantum Cryptography Based on Artificial Neural Networks,” Quantum Information Processing, vol. 18, no. 6, 2019.
H. Gómez, Ó. Reyes, and E. Roa, “A 65nm CMOS Key Establishment Core Based on Tree Parity Machines,” Integration, vol. 58, pp. 430–437, 2017.
M. Dolecki and R. Kozera, “The Impact of the TPM Weights Distribution on Network Synchronization Time,” in Computer Information Systems and Industrial Management, pp. 451–460, 2015.
S. Chakraborty, J. Dalal, B. Sarkar, and D. Mukherjee, “Neural Synchronization Based Secret Key Exchange over Public Channels: A Survey,” arXiv preprint, 2015.
P. Revankar, W. Gandhare, and D. Rathod, “Private Inputs to Tree Parity Machine,” in Proceedings of Semantics Scholar, 2010.
A. Klimov, A. Mityagin, and A. Shamir, “Analysis of Neural Cryptography,” in Advances in Cryptology – EUROCRYPT 2002, L. R. Knudsen, Ed. Berlin: Springer, pp. 288–298, 2002.
I. Kanter and W. Kinzel, “Neural Cryptography,” in Proc. 9th Int. Conf. on Neural Information Processing (ICONIP ’02), Singapore: IEEE, pp. 1351–1354, 2002, doi: 10.1109/ICONIP.2002.1202841.
I. Kanter, W. Kinzel, and E. Kanter, “Secure Exchange of Information by Synchronization of Neural Net,” Europhysics Letters, vol. 57, no. 1, pp. 141–147, 2002.
W. Kinzel and I. Kanter, “Interacting Neural Networks and Cryptography,” in Advances in Solid State Physics, B. Kramer, Ed., vol. 42, Berlin: Springer, pp. 383–391, 2002.
R. Metzler, W. Kinzel, and I. Kanter, “Interacting Neural Networks,” Physical Review E, vol. 62, no. 2, pp. 2555–2565, 2000.
W. Kinzel, R. Metzler, and I. Kanter, “Dynamics of Interacting Neural Networks,” Journal of Physics A: Mathematical and General, vol. 33, no. 14, pp. L141–L147, 2000.
F. T. Arecchi, “Chaotic Neuron Dynamics, Synchronization, and Feature Binding: Quantum Aspects,” Australian National University, 2003.
I. Kanter and W. Kinzel, The Theory of Neural Networks and Cryptography, Minerva Center, Bar-Ilan University, Israel, 2003.
J. Hertz, A. Krogh, and R. G. Palmer, Introduction to the Theory of Neural Computation, Redwood City, CA: Addison-Wesley, 1991.
L. Columbus, “2018 Roundup of Internet of Things Forecasts and Market Estimates,” Forbes, accessed May 10, 2020.
M. Thomsen, “Microsoft's Deep Learning Project Outperforms Humans in Image Recognition,” Forbes, accessed Feb. 19, 2020.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
The ownership of copyright remains with the Authors.
Authors may use their own material in other publications provided that the Journal is acknowledged as the original place of publication and National Technical University of Ukraine “Igor Sikorsky Kyiv Polytechnic Institute” as the Publisher.
ITS articles are published under Creative Commons licence:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under CC BY 4.0that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
