Statistical Proof of Execution (SPEX)

2025-03-24

AI Summary

AI-driven autonomous decision-making suffers from unverifiable reasoning processes and compromised verification robustness due to non-deterministic interference. Method: This paper proposes a lightweight, statistically sampled verifiable computing protocol. It formally defines “execution provability” and innovatively replaces traditional cryptographic proofs with efficient statistical sampling—ensuring verification reliability while drastically reducing overhead. The approach integrates uncertainty modeling, adaptation strategies for non-deterministic environments, and a lightweight verification mechanism to systematically address verification failures caused by stochasticity and environmental perturbations. Contribution/Results: Experiments demonstrate a 10×–100× reduction in verification overhead, enabling high-throughput, low-latency real-time inference verification. The protocol is empirically validated in autonomous driving and edge-AI decision-making scenarios, confirming its practical efficacy and scalability.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Reasoning under Uncertainty: Stochastic Optimization
• Computer Vision: Adversarial Attacks & Robustness

Application Category

• Security and Privacy: Data transparency and provenance
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

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.

Problem

• Ensuring verifiable computing in autonomous decision-making systems
• Developing a faster and cost-effective sampling-based protocol
• Addressing non-determinism challenges with effective strategies

Innovation

• Sampling-based protocol for verifiable computing
• Faster and cost-effective than existing methods
• Strategies to manage non-determinism challenges