Machine Learning-Based Randomness Analysis For a Auantum Random Number Generator
Year: 2024
Type: conference-paper
Abstract: Random numbers are critical to information security. Quantum random numbers are theoretically truly random and unpredictable. However, the measurement process of a quantum random number generator (QRNG) can be affected by environmental disturbances that compromise the integrity of the generated random numbers. A machine learning model is proposed to assess the stochasticity of the continuous variable QRNG under the influence of vacuum noise. The model is designed to detect the correlation between the randomness of the QRNG being corrupted under the influence of classical noise (electrical noise). In addition, our model detects a decrease in the randomness of the QRNG random numbers when the electrical noise intensity increases to a certain correlation. The results show that machine learning (ML) can be used as a measure of the quality of QRNG.
Authors: Wanlin Du, Ling Wang, Yuanzhe Zhu, Hong Lv
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: diamond
OpenAlex ID: W4402635692