Neural Network Based Min-entropy Estimation for Random Number Generators
Random Number Generators (RNGs) are essential for cryptographic systems and communication security. A cryptographic application is prone to have a serious security risk if the entropy source that generates the random number cannot provide sufficient randomness (unpredictability) as expected. The min-entropy is usually employed to evaluate the unpredictability, which measures the difficulty of guessing the most likely output of RNGs. Recently, predictors for min-entropy estimation are proposed in the NIST 800-90B (90B), which attempt to predict the next sample in a sequence based on all previous samples. However, these predictors have shortfalls in evaluating random number with long dependence and multivariate due to huge time complexity (i.e., high-order polynomial time complexity). From the concept of predictors, we provide several suitable and efficient predictors based on neural networks for min-entropy estimation. The neural networks apply to approximating the Probability Distribution Function (PDF) and have a linear complexity of the sample space. Compared to the 90B’s predictors, the experimental results on various simulated source demonstrate that our proposed predictors have a comparable accuracy, and the execution efficiency has a significant improvement. Furthermore, when the sample space is over \(2^2\) and sample size is over \(10^8\), the 90B’s predictors cannot give the estimated result. Instead, our proposed predictors still can provide an accurate result.
KeywordsRandom number Neural network Entropy estimation Predictor
This work was partially supported by National Natural Science Foundation of China (No. 61602476 and No. 61772518), and Cryptography Development Foundation of China (No. MMJJ20170205).
- 5.Donate, J.P., Li, X., Sánchez, G.G., de Miguel, A.S.: Time series forecasting by evolving artificial neural networks with genetic algorithms, differential evolution and estimation of distribution algorithm. Neural Comput. Appl. 22(1), 11–20 (2013). https://doi.org/10.1007/s00521-011-0741-0CrossRefGoogle Scholar
- 10.Gutterman, Z., Pinkas, B., Reinman, T.: Analysis of the linux random number generator. In: 2006 IEEE Symposium on Security and Privacy (S&P 2006), 21–24 May 2006, Berkeley, California, USA, pp. 371–385 (2006)Google Scholar
- 11.Hagerty, P., Draper, T.: Entropy bounds and statistical tests. https://csrc.nist.gov/csrc/media/events/random-bit-generation-workshop-2012/documents/hagerty_entropy_paper.pdf
- 12.ISO/IEC JTC 1/SC 27, Berlin, Germany: ISO/IEC 18031: Information technology - Security techniques - Random bit generation (2011)Google Scholar
- 16.Killmann, W., Schindler, W.: AIS 31: Functionality Classes and Evaluation Methodology for True (Physical) Random Number Generators. Version 3.1. T-Systems GEI GmbH and Bundesamt fr Sicherheit in der Informationstechnik (BSI), Bonn, Germany (2001)Google Scholar
- 18.Luna-Sanchez, J.C., Gómez-Ramírez, E., Najim, K., Ikonen, E.: Forecasting time series with a logarithmic model for the polynomial artificial neural networks. In: The 2011 International Joint Conference on Neural Networks, IJCNN 2011, San Jose, California, USA, 31 July–5 August 2011, pp. 2725–2732 (2011). https://doi.org/10.1109/IJCNN.2011.6033576
- 21.NIST: The NIST Statistical Test Suite (2010). http://csrc.nist.gov/groups/ST/toolkit/rng/documents/sts-2.1.2.zip
- 22.Turan, M.S., Barker, E., Kelsey, J., McKay, K., Baish, M., Boyle, M.: (Second Draft) NIST special publication 800-90B: recommendation for the entropy sources used for random bit generation, January 2016. https://csrc.nist.gov/CSRC/media/Publications/sp/800-90b/draft/documents/sp800-90b_second_draft.pdf
- 23.Vanhoef, M., Piessens, F.: Predicting, decrypting, and abusing WPA2/802.11 group keys. In: 25th USENIX Security Symposium, USENIX Security 16, Austin, TX, USA, 10–12 August 2016, pp. 673–688 (2016)Google Scholar
- 25.Yang, J., Ma, Y., Chen, T., Lin, J., Jing, J.: Extracting more entropy for TRNGs based on coherent sampling. In: Deng, R., Weng, J., Ren, K., Yegneswaran, V. (eds.) SecureComm 2016. LNICSSITE, vol. 198, pp. 694–709. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-59608-2_38CrossRefGoogle Scholar
- 26.Zhu, S., Ma, Y., Chen, T., Lin, J., Jing, J.: Analysis and improvement of entropy estimators in NIST SP 800-90B for Non-IID entropy sources. IACR Trans. Symmetric Cryptol. 2017(3), 151–168 (2017)Google Scholar
- 27.Zhu, S., Ma, Y., Lin, J., Zhuang, J., Jing, J.: More powerful and reliable second-level statistical randomness tests for NIST SP 800-22. In: Proceedings Advances in Cryptology - ASIACRYPT 2016 - 22nd International Conference on the Theory and Application of Cryptology and Information Security, Hanoi, Vietnam, 4–8 December 2016, Part I, pp. 307–329 (2016)CrossRefGoogle Scholar