GAN-based pseudo random number generation optimized through genetic algorithms
Abstract Pseudo-random number generators (PRNGs) are deterministic algorithms that generate sequences of numbers approximating the properties of random numbers, which are widely utilized in various fields. In this paper, we present a Genetic Algorithm Optimized Generative Adversarial Network (herein...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2024-11-01
|
| Series: | Complex & Intelligent Systems |
| Subjects: | |
| Online Access: | https://doi.org/10.1007/s40747-024-01606-w |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832571145400877056 |
|---|---|
| author | Xuguang Wu Yiliang Han Minqing Zhang Yu Li Su Cui |
| author_facet | Xuguang Wu Yiliang Han Minqing Zhang Yu Li Su Cui |
| author_sort | Xuguang Wu |
| collection | DOAJ |
| description | Abstract Pseudo-random number generators (PRNGs) are deterministic algorithms that generate sequences of numbers approximating the properties of random numbers, which are widely utilized in various fields. In this paper, we present a Genetic Algorithm Optimized Generative Adversarial Network (hereinafter referred to as GAGAN), which is designed for the effective training of discrete generative adversarial networks. In situations where non-differentiable activation functions, such as the modulo operation, are employed and traditional gradient-based backpropagation methods are inapplicable, genetic algorithms are utilized to optimize the parameters of the generator network. Based on this framework, we propose a novel recursive PRNG. Given that a PRNG can be constructed from one-way functions and their associated hardcore predicates, our proposed generator consists of two neural networks that simulate these functions and serve as the state transition function and the output function, respectively. The proposed PRNG has been rigorously tested using stringent benchmarks such as the NIST Statistical Test Suite (SP800-22) and the Chinese standard for random number generation (GM/T 0005-2021). Additionally, it has demonstrated outstanding performance in terms of Hamming distance. The results indicate that the proposed GAN-based PRNG has achieved a high degree of randomness and is highly sensitive to variations in the input. |
| format | Article |
| id | doaj-art-15b1361238b04451a21b21d4cca3290a |
| institution | Kabale University |
| issn | 2199-4536 2198-6053 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | Springer |
| record_format | Article |
| series | Complex & Intelligent Systems |
| spelling | doaj-art-15b1361238b04451a21b21d4cca3290a2025-02-02T12:48:58ZengSpringerComplex & Intelligent Systems2199-45362198-60532024-11-0111111610.1007/s40747-024-01606-wGAN-based pseudo random number generation optimized through genetic algorithmsXuguang Wu0Yiliang Han1Minqing Zhang2Yu Li3Su Cui4College of Cryptography Engineering, Engineering University of People’s Armed PoliceCollege of Cryptography Engineering, Engineering University of People’s Armed PoliceCollege of Cryptography Engineering, Engineering University of People’s Armed PoliceCollege of Cryptography Engineering, Engineering University of People’s Armed PoliceCollege of Cryptography Engineering, Engineering University of People’s Armed PoliceAbstract Pseudo-random number generators (PRNGs) are deterministic algorithms that generate sequences of numbers approximating the properties of random numbers, which are widely utilized in various fields. In this paper, we present a Genetic Algorithm Optimized Generative Adversarial Network (hereinafter referred to as GAGAN), which is designed for the effective training of discrete generative adversarial networks. In situations where non-differentiable activation functions, such as the modulo operation, are employed and traditional gradient-based backpropagation methods are inapplicable, genetic algorithms are utilized to optimize the parameters of the generator network. Based on this framework, we propose a novel recursive PRNG. Given that a PRNG can be constructed from one-way functions and their associated hardcore predicates, our proposed generator consists of two neural networks that simulate these functions and serve as the state transition function and the output function, respectively. The proposed PRNG has been rigorously tested using stringent benchmarks such as the NIST Statistical Test Suite (SP800-22) and the Chinese standard for random number generation (GM/T 0005-2021). Additionally, it has demonstrated outstanding performance in terms of Hamming distance. The results indicate that the proposed GAN-based PRNG has achieved a high degree of randomness and is highly sensitive to variations in the input.https://doi.org/10.1007/s40747-024-01606-wAdversarial neural networksPseudo-random number generatorsNeural cryptography |
| spellingShingle | Xuguang Wu Yiliang Han Minqing Zhang Yu Li Su Cui GAN-based pseudo random number generation optimized through genetic algorithms Complex & Intelligent Systems Adversarial neural networks Pseudo-random number generators Neural cryptography |
| title | GAN-based pseudo random number generation optimized through genetic algorithms |
| title_full | GAN-based pseudo random number generation optimized through genetic algorithms |
| title_fullStr | GAN-based pseudo random number generation optimized through genetic algorithms |
| title_full_unstemmed | GAN-based pseudo random number generation optimized through genetic algorithms |
| title_short | GAN-based pseudo random number generation optimized through genetic algorithms |
| title_sort | gan based pseudo random number generation optimized through genetic algorithms |
| topic | Adversarial neural networks Pseudo-random number generators Neural cryptography |
| url | https://doi.org/10.1007/s40747-024-01606-w |
| work_keys_str_mv | AT xuguangwu ganbasedpseudorandomnumbergenerationoptimizedthroughgeneticalgorithms AT yilianghan ganbasedpseudorandomnumbergenerationoptimizedthroughgeneticalgorithms AT minqingzhang ganbasedpseudorandomnumbergenerationoptimizedthroughgeneticalgorithms AT yuli ganbasedpseudorandomnumbergenerationoptimizedthroughgeneticalgorithms AT sucui ganbasedpseudorandomnumbergenerationoptimizedthroughgeneticalgorithms |