Machine Learning Cryptanalysis of a Quantum Random Number Generator

TL;DR

This paper uses machine learning to analyze and benchmark the security and randomness quality of quantum random number generators, revealing how classical noise impacts their unpredictability and robustness.

Contribution

It introduces a machine learning approach to detect classical noise effects in QRNGs and assesses their robustness against ML-based prediction attacks.

Findings

ML detects correlations caused by classical noise in QRNGs

Filtering improves QRNG robustness against ML prediction

ML can benchmark and evaluate RNG device quality

Abstract

Random number generators (RNGs) that are crucial for cryptographic applications have been the subject of adversarial attacks. These attacks exploit environmental information to predict generated random numbers that are supposed to be truly random and unpredictable. Though quantum random number generators (QRNGs) are based on the intrinsic indeterministic nature of quantum properties, the presence of classical noise in the measurement process compromises the integrity of a QRNG. In this paper, we develop a predictive machine learning (ML) analysis to investigate the impact of deterministic classical noise in different stages of an optical continuous variable QRNG. Our ML model successfully detects inherent correlations when the deterministic noise sources are prominent. After appropriate filtering and randomness extraction processes are introduced, our QRNG system, in turn, demonstrates its robustness against ML. We further demonstrate the robustness of our ML approach by applying it to uniformly distributed random numbers from the QRNG and a congruential RNG. Hence, our result shows that ML has potentials in benchmarking the quality of RNG devices.