Secure Communication Based On Key Generation With Quantum Reinforcement Learning

Abstract

Data security and secure communication is one of the most important issues of today. In this study, a quantum-based method for secure communication is proposed. In the proposed method, the necessary secret key in communication is generated locally by each participant through quantum gates. The quantum gates are taught by using quantum reinforcement learning (QRL). Proposed study is simulated using the Qiskit library for Python. Proposed study performs the learning action with an accuracy of 87.95% for 195 gates, 85.47% for 128 gates, 83.59% for 64 gates, 76.25% for 32 gates. As the key size increases, the performance of the method increases. The participants don’t share the secret key in the presented method. Thus, the communication becomes more secure. In the study, the method is also examined in terms of security. Security analysis shows that the proposed method provide secure communication.

Keywords

• quantum reinforcement learning
• key generation
• quantum key distribution
• quantum cryptography

References

1. [1] D. Dong, C. Chen, H. Li, and T. Z. Tarn, “Quantum reinforcement learning,” IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), vol. 38, no. 5, pp. 1207– 1220, 2008.
2. [2] Z. A. Ren, Y. P. Chen, J. Y. Liu, and Q. W. H. J. Ding, “Implementation of machine learning in quantum key distributions,” IEEE Communıcatıons Letters, vol. 25, no. 3, pp. 940–944, 2021.
3. [3] S. Zhang, J. Liu, G. Zeng, C. Zhang, X. Zhou, and Q. Wang, “Machine learning-assisted measurement device-independent quantum key distribution on reference frame calibration,” Entropy, vol. 23, no. 10, p. 1242, 2021.
4. [4] H. Chin, N. Jain, D. Zibar, U. Andersen, and T. Gehring, “Machine learning aided carrier recovery in continuous-variable quantum key distribution,” Quantum Information, vol. 7, no. 20, 2021.
5. [5] S. Giordano and M. A. Martin-Delgado, “Reinforcementlearning generation of four-qubit entangled states,” Physical Review Research, vol. 4, no. 4, p. 043056, 2022.
6. [6] K. Kashyap, Lalit, D. Shah, and L. Gautam, “From classical to quantum: A review of recent progress in reinforcement learning,” presented at 2021 2nd International Conference for Emerging Technology (INCET), Belgaum, India, 2013.
7. [7] J. D. Mart´ın-Guerrero and L. Lamata, “Quantum machine learning: A tutoria,” Neurocomputing, vol. 470, pp. 457–461, 2022.
8. [8] N. Meyer, C. Ufrecht, M. Periyasamy, D. D. Scherer, A. Plinge, and C. Mutschler, “A survey on quantum reinforcement learning.” arXiv preprint, arXiv:2211.03464, 2022.

9. [9] F. Albarr´an-Arriagada, J. C. Retamal, E. Solano, and L. Lamata, “Measurement-based adaptation protocol with quantum reinforcement learning,” Phys. Rev. A, vol. 98, no. 4, p. 042315, 2018.
10. [10] M. Moll and L. Kunczik, “Comparing quantum hybrid reinforcement learning to classical methods,” Human Intelligent Systems Integration, vol. 3, pp. 15–23, 2021.
11. [11] M. Franz, L. Wolf, M. Periyasamy, C. Ufrecht, D. D. Scherer, A. Plinge, C. Mutschler, and W. Mauerera, “Uncovering instabilities in variational-quantum deep q-networks,” Journal of the Franklin Institute, 2022.
12. [12] IBM, “Qiskit,” Accessed Mar. 11, 2023. [Online]. Available: https://qiskit.org/