Raw QPP-RNG randomness via system jitter across platforms: a NIST SP 800-90B evaluation

Area of Science:

• Computer Science
• Cryptography
• Hardware Security

Background:

• High-quality randomness is essential for modern cryptographic systems.
• Existing true random number generators (TRNGs) often rely on specialized hardware or have limitations in entropy density.
• System-level jitters present an untapped source of entropy.

Purpose of the Study:

• To introduce QPP-RNG, a novel TRNG leveraging system-level jitters for cryptographic randomness.
• To evaluate the performance and statistical properties of QPP-RNG across diverse platforms.
• To demonstrate the feasibility of generating strong randomness on commodity hardware without specialized components.

Main Methods:

• Harvesting entropy from diverse system-level jitters (CPU pipeline timing, DRAM refresh, cache misses).
• Measuring elapsed time of randomized array sorting operations perturbed by microscopic jitters.
• Amplifying timing variations into cryptographically strong randomness using a quantum permutation pad (QPP) architecture.
• Rigorous statistical evaluation using NIST SP 800-90B, NIST SP 800-22, and ENT test suites.

Main Results:

• QPP-RNG achieved high IID min-entropy (7.7-7.9 bits/byte) across Windows, macOS, and Raspberry Pi.
• Consistently passed NIST SP 800-90B IID tests with p-values significantly above the 0.01 threshold.
• Demonstrated remarkable statistical consistency across x86_64 and ARM64 architectures.
• Outperformed leading commercial entropy sources in terms of entropy density.

Conclusions:

• QPP-RNG provides a novel paradigm for embedded security by transforming system noise into a reliable entropy stream.
• It offers a robust, high-quality entropy source on general-purpose devices, suitable for resource-constrained IoT and edge computing.
• The approach eliminates the need for specialized hardware, making strong randomness more accessible.