Abstract
Random number generators are of paramount importance in numerous fields. Under certain well-defined adversarial settings, True Random Number Generators (TRNGs) are more secure than their computational (pseudo) random number generator counterparts. TRNGs are also known to be more efficiently implemented on hardware platforms where, for various applications, efficiency in terms of electronic cost factors is critical. In this manuscript, we first provide an evaluation of robustness and reliability of efficient time-domain-based TRNG implementation over FPGA platform. In particular, we demonstrate sensitivities which imply a TRNG construction which is not agnostic to electronic-design-automation tools and to the level of designers’ know-how. This entails a large amount of effort and validation to make the designs robust, as well as requires a high degree of complexity from non-trivial FPGAs flows. This motivates the second part of the manuscript, where we propose an ASIC-based implementation of the TRNG, along with the optimization steps to enhance its characteristics. The optimized design improves the randomness-throughput by 42× for the same entropy level described in previous works, and it can provide maximal entropy level of 0.985 with 7× improvement in randomness throughput over the raw samples (no pre-processing). The proposed design simultaneously provides a reduced energy of 0.1 (mW/bit) for the same entropy level as previous works, and 1.06 (mW/bit) for the higher entropy flavor, and a lower area utilization of 0.000252 (mm2) on a 65 nm technology evaluation, situating it in the top-class of the discuss ratings. This leads to the quantitative question of the gain in electronic cost factors over ASIC TRNGs, and the minimum Cost Per Bit/Source possible to date. Finally, we exemplify a TRNG versus PRNG cost-extrapolation for security architects and designers, targeting an ASIC scenario feeding a lightweight encryption core.
Highlights
Random number generators have various applications in statistics, probabilistic algorithms, simulations, cryptography, and other fields where producing an unpredictable result is desired
The optimized design improves in randomness-throughput by 42× for the same entropy level described in previous works, and it can even provide a considerably improved entropy level of 0.985 with 7× improvement in randomness throughput
We demonstrated sensitivities which result in a True Random Number Generators (TRNGs) construction that is not agnostic to electronic-design-automation tools and to designers’ know-how
Summary
Random number generators have various applications in statistics, probabilistic algorithms, simulations, cryptography, and other fields where producing an unpredictable result is desired. There are two main groups of random number generators: True Random Number Generators (TRNGs) which extract randomness from physical noise, and Pseudo Random Number Generators (PRNGs) which appear statistically random but are predictable. Feedback Shift Registers (LFSR), such as in References [1,2], and encryption in some modeof-operation, e.g., the Advanced Encryption Standard in Counter mode (AES-CTR DRBG). These types of RNGs require an initial vector (seed) as a starting condition. A TRNG is a device that relies on a random physical process and extracts random numbers from it
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
