A model for identifying the source of pseudorandom number sequences based on a hybrid neural network

Authors

DOI:

https://doi.org/10.18372/2073-4751.78.18965

Keywords:

random number generators, source identification, hybrid neural network, recurrent neural networks, convolutional neural networks, cryptography, machine learning, classification, data security

Abstract

This article presents a model for identifying random number sources based on a hybrid neural network. The proposed model combines recurrent (RNN) and convolutional (CNN) neural networks to achieve high classification accuracy. The study discusses the key stages of model development, including data preparation, model construction, training, and performance evaluation. Experimental results confirm that the model can effectively identify random number sources with an accuracy of more than 95% for some generators. The developed approach provides high reliability and can be applied in various fields, including cryptography and modeling.

References

Pasqualini L., Parton M. Pseudo random number generation: A reinforcement learning approach. Procedia Computer Science. 2020. Vol. 170. P. 1122–1127. DOI: 10.1016/j.procs.2020.03.057.

Hochreiter S., Schmidhuber J. Long short-term memory. Neural Computation. 1997. Vol. 9, iss. 8. P. 1735–1780. DOI: 10.1162/neco.1997.9.8.1735.

LeCun Y., Bengio Y. Convolutional networks for images, speech, and time series. Handbook of Brain Theory and Neural Networks / ed. by M. A. Arbib. Cambridge, MA, 1998. P. 255–258.

Park S. et al. Dynamical pseudo-random number generator using reinforcement learning. Applied Sciences. 2022. Vol. 12, iss. 7. 3377. DOI: 10.3390/app12073377.

Haylock B. et al. Multiplexed quantum random number generation. Quantum. 2019. Vol. 3. P. 141. DOI: 10.22331/q-2019-04-26-141.

Amigo G. et al. Forecasting Pseudo Random Numbers Using Deep Learning. 2021 15th International Conference on Signal Processing and Communication Systems (ICSPCS) : proceedings, Sydney, Australia, 13–15 December, 2021 / IEEE. 2021. P. 1–7. DOI: 10.1109/ICSPCS53099.2021.9660301.

Proskurin D., Gnatyuk S., Okhrimenko T. Predicting Pseudo-Random and Quantum Random Number Sequences using Hybrid Deep Learning Models. Modern Machine Learning Technologies and Data Science Workshop (MoMLeT&DS 2023) : proceedings, Lviv, Ukraine, June 3, 2023 / 2023. P. 77–88. URL: https://ceur-ws.org/Vol-3426/paper7.pdf.

Li C. et al. Deep Learning-Based Security Verification for a Random Number Generator Using White Chaos. Entropy. 2020. Vol. 22, iss. 10. 1134. DOI: 10.3390/e22101134

Akhshani A. et al. Pseudo random number generator based on quantum chaotic map. Communications in Nonlinear Science and Numerical Simulation. 2014. Vol. 19, iss. 1. P. 101–111.

Wang Y. et al. A pseudorandom number generator based on piecewise logistic map. Nonlinear Dynamics. 2016. Vol. 83. P. 2373–2391.

Merah L. et al. A pseudo random number generator based on the chaotic system of Chua's circuit. Applied Mathematical Sciences. 2013. Vol. 7, iss. 55. P. 2719–2734.

Published

2024-07-01

Issue

Section

Статті