Random number generator (RNG) is a fundamental and important cryptographic element, which has made an outstanding contribution to guaranteeing the network and communication security of cryptographic applications in the Internet age. In reality, if the random number used cannot provide sufficient randomness (unpredictability) as expected, these cryptographic applications are vulnerable to security threats and cause system crashes. Min-entropy is one of the approaches that are usually employed to quantify the unpredictability. The NIST Special Publication 800-90B adopts the concept of min-entropy in the design of its statistical entropy estimation methods, and the predictive model-based estimators added in the second draft of this standard effectively improve the overall capability of the test suite. However, these predictors have problems on limited application scope and high computational complexity, e.g., they have shortfalls in evaluating random numbers with long dependence and multivariate due to the huge time complexity (i.e., high-order polynomial time complexity). Fortunately, there has been increasing attention to using neural networks to model and forecast time series, and random numbers are also a type of time series. In our work, we propose several new and efficient approaches for min-entropy estimation by using neural network technologies and design a novel execution strategy for the proposed entropy estimation to make it applicable to the validation of both stationary and nonstationary sources. Compared with the 90B’s predictors officially published in 2018, the experimental results on various simulated and real-world data sources demonstrate that our predictors have a better performance on the accuracy, scope of applicability, and execution efficiency. The average execution efficiency of our predictors can be up to 10 times higher than that of the 90B’s for 10 6 sample size with different sample spaces. Furthermore, when the sample space is over 2 2 and the sample size is over 10 8 , the 90B’s predictors cannot give estimated results. Instead, our predictors can still provide accurate results. Copyright© 2019 John Wiley & Sons, Ltd.

Widely used as fundamental security components in most cryptographic applications, random number generators (RNGs) rely mainly on randomness provided by entropy sources. If the provided randomness is less than expected, RNGs may be compromised and thus impair the security of the whole cryptographic applications. However, the common assumptions (e.g., outputs are independent and identically distributed, i.e., IID) may not always hold. For example, many entropy sources are based on some physical phenomena that are fragile and sensitive to external factors (e.g., temperature), which means the distributions of these entropy sources' outputs are continuously changing. As important tools to measure the quality of entropy sources, existing entropy estimation methods may provide false estimations against these time-varying data, because they cannot detect the changes of data distributions. In this paper, we firstly review and analyze the existing typical entropy estimators including the NIST SP 800-90B (90B for short) estimators and the lately proposed neural network based (NN-based) estimators, especially, their limitations on the aforementioned time-varying data. Second, we propose an entropy estimation framework adopting change detection techniques to address this problem. In contrast to the NN-based estimators, the proposed estimator under this framework employs a change detection method to preprocess the tested data and adds additional distribution features to each data sample, which makes it possible to learn the distribution changes and estimate the entropy more accurately. Finally, we evaluate the performance of our estimator using various kinds of simulated data and real world data, and compare our estimator with the 90B estimators and the NN-based estimators. Extensive evaluations demonstrate that the proposed estimator provides similar or more accurate entropy estimation than the other estimators, especially for time-varying data.