ZK-Audit: A Universal Privacy-Preserving Verification Framework for Autonomous Driving Simulators

Giwoong Kim, Youjeong Son, Shiho Kim

Keywords: Autonomous Driving, Zero-Knowledge Proofs, Blockchain, Simulation, Privacy-Preserving Verification

Abstract: As autonomous driving technology advances towards Level 4 and 5, virtual simulation has become an indispensable tool for safety validation. However, a critical "trust gap" exists between developers and regulators; submitting raw simulation logs poses risks of data tampering (integrity issues) and intellectual property leakage (privacy issues). To address this, we propose ZK-Audit, a universal, privacy-preserving verification framework designed to interface with various autonomous driving simulators. By leveraging Zero-Knowledge Proofs and blockchain technology, ZK-Audit allows a Prover to cryptographically demonstrate that a simulation run adhered to specific safety constraints such as collision avoidance and speed limits without revealing the underlying telemetry data. This paper outlines the simulation-agnostic system architecture and constraint logic, offering a scalable solution for decentralized, trust-free certification in the Web 4.0 mobility era.

Email Sharing: We authorize the sharing of all author emails with Program Chairs.

Data Release: We authorize the release of our submission and author names to the public in the event of acceptance.

Submission Number: 14