Zhuo Tingting (Peter the Great St. Petersburg Polytechnic University )
| |
This article presents the results of a study on the effectiveness of using quantum key distribution (QKD) technology in combination with machine learning (ML) methods to enhance the security of modern communication systems. An analysis of relevant publications from recent years revealed growing interest within the scientific community in the potential of quantum cryptography and artificial intelligence in the field of information security. The aim of this research was an empirical assessment of the effectiveness of hybrid QKD-ML protocols compared to traditional cryptographic methods. To achieve this goal, simulation modeling, statistical analysis, and machine learning on a sample of 1,000 simulated attacks on communication channels were used. The results obtained demonstrated that the use of QKD-ML protocols increases system resistance to hacking by 56.7% (p<0.01) and reduces response time to threats by 41.2% (p<0.05) in comparison with classical algorithms. Furthermore, the application of ML methods for dynamic optimization of quantum channel parameters ensured a 23.8% (p<0.05) increase in the speed of key generation and distribution. The theoretical significance of the study lies in the development of conceptual foundations for applying quantum information technologies in cybersecurity. The practical value of the results is associated with the possibility of using them to develop highly secure next-generation communication systems. Future research prospects include exploring the scalability of QKD-ML solutions for global multi-node networks.
Keywords:Quantum key distribution, machine learning, cybersecurity, communication systems, quantum cryptography
|
|
| |
|
Read the full article …
|
Citation link:
Zhuo T. STUDY OF THE EFFICIENCY OF QUANTUM KEY DISTRIBUTION IN SECURE COMMUNICATION SYSTEMS USING MACHINE LEARNING // Современная наука: актуальные проблемы теории и практики. Серия: Естественные и Технические Науки. -2025. -№02. -С. 159-163 DOI 10.37882/2223-2966.2025.02.38 |
|
|
LEGAL
INFORMATION:
