Pseudo-Random Number Generation using Generative Adversarial Networks

TL;DR

This paper proposes using generative adversarial networks to create pseudo-random number generators that produce sequences with strong statistical properties, outperforming some standard non-cryptographic PRNGs.

Contribution

It introduces a novel GAN-based approach for PRNGs, including modifications to the architecture to enhance unpredictability and security.

Findings

GAN-based PRNGs pass around 99% of NIST tests

The approach outperforms several standard non-cryptographic PRNGs

Effective training of small neural networks for pseudo-random sequences

Abstract

Pseudo-random number generators (PRNG) are a fundamental element of many security algorithms. We introduce a novel approach to their implementation, by proposing the use of generative adversarial networks (GAN) to train a neural network to behave as a PRNG. Furthermore, we showcase a number of interesting modifications to the standard GAN architecture. The most significant is partially concealing the output of the GAN's generator, and training the adversary to discover a mapping from the overt part to the concealed part. The generator therefore learns to produce values the adversary cannot predict, rather than to approximate an explicit reference distribution. We demonstrate that a GAN can effectively train even a small feed-forward fully connected neural network to produce pseudo-random number sequences with good statistical properties. At best, subjected to the NIST test suite, the trained generator passed around 99% of test instances and 98% of overall tests, outperforming a number of standard non-cryptographic PRNGs.