Statistical Proof of Execution (SPEX)
This addresses the need for reliable verification in automated systems, which is crucial for safety and trust in real-world applications, though it appears incremental by building on existing verifiable computing methods.
The paper tackles the problem of verifiable computing in autonomous decision-making by introducing a sampling-based protocol that is faster, more cost-effective, and simpler than existing methods, and it addresses non-determinism with strategies for common scenarios.
Many real-world applications are increasingly incorporating automated decision-making, driven by the widespread adoption of ML/AI inference for planning and guidance. This study examines the growing need for verifiable computing in autonomous decision-making. We formalize the problem of verifiable computing and introduce a sampling-based protocol that is significantly faster, more cost-effective, and simpler than existing methods. Furthermore, we tackle the challenges posed by non-determinism, proposing a set of strategies to effectively manage common scenarios.