Omid Kavehei

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.

Two coveted qualities for a random number generator (RNG) are uniformity and unpredictability. A Pseudo-RNG (PRNG) produces a uniform output, but it is predictable when one has knowledge of the seed and implementation parameters. While a quantum-RNG (QRNG) produces an unpredictable output, it is not necessarily uniform and hence typically requires randomness extraction. We examine these two aspects in RNGs by utilizing a machine learning cryptanalysis, showing the applicability of the tool in uncovering hidden correlations and implementation failures.