Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Hermes Seal: Zero-Knowledge Assurance for Autonomous Vehicle Communications

Munawar Hasan, Apostol Vassilev, Edward Griffor, Thoshitha Gamage

Abstract

The application of zero-knowledge proofs (ZKPs) in autonomous systems is an emerging area of research, motivated by the growing need for regulatory compliance, transparent auditing, and trustworthy operation in decentralized environments. zk-SNARK is a powerful cryptographic tool that allows a party (the prover) to prove to another party (the verifier) that a statement about its own internal state is true, without revealing sensitive or proprietary data about that state. This paper proposes Hermes Seal: a zk-SNARK-based ZKP framework for enabling privacy-preserving, verifiable communication in vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) networks. The framework allows autonomous systems to generate cryptographic proofs of perception and decision-related computations without revealing proprietary models, sensor data, or internal system states, thereby supporting interoperability across heterogeneous autonomous systems. We present two real-world case studies implemented and empirically evaluated within our framework, demonstrating a step toward verifiable autonomous system information exchanges. The first demonstrates real-time proof generation and verification, achieving 8 ms proof generation and 1 ms verification on a GPU, while the second evaluates the performance of an autonomous vehicle perception stack, enabling proof of computation without exposing proprietary or confidential data. Furthermore, the framework can be integrated into AV perception stacks to facilitate verifiable interoperability and privacy-preserving cooperative perception. The demonstration code for this project is open source, available on Github.

Hermes Seal: Zero-Knowledge Assurance for Autonomous Vehicle Communications

Abstract

The application of zero-knowledge proofs (ZKPs) in autonomous systems is an emerging area of research, motivated by the growing need for regulatory compliance, transparent auditing, and trustworthy operation in decentralized environments. zk-SNARK is a powerful cryptographic tool that allows a party (the prover) to prove to another party (the verifier) that a statement about its own internal state is true, without revealing sensitive or proprietary data about that state. This paper proposes Hermes Seal: a zk-SNARK-based ZKP framework for enabling privacy-preserving, verifiable communication in vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) networks. The framework allows autonomous systems to generate cryptographic proofs of perception and decision-related computations without revealing proprietary models, sensor data, or internal system states, thereby supporting interoperability across heterogeneous autonomous systems. We present two real-world case studies implemented and empirically evaluated within our framework, demonstrating a step toward verifiable autonomous system information exchanges. The first demonstrates real-time proof generation and verification, achieving 8 ms proof generation and 1 ms verification on a GPU, while the second evaluates the performance of an autonomous vehicle perception stack, enabling proof of computation without exposing proprietary or confidential data. Furthermore, the framework can be integrated into AV perception stacks to facilitate verifiable interoperability and privacy-preserving cooperative perception. The demonstration code for this project is open source, available on Github.

Paper Structure

This paper contains 44 sections, 2 theorems, 27 equations, 7 figures, 4 tables, 7 algorithms.

Table of Contents

  1. Introduction
  2. A Primer on Zero-Knowledge Proofs
  3. Interactive vs Non-Interactive Proof
  4. Computational Constraints in AVs
  5. The zk-SNARK Protocol
  6. Preliminaries and Notation
  7. Data Representation
  8. Hermes' Seal: A ZKP-based Framework for AVs
  9. Design Philosophy
  10. System Model and Entities
  11. Entity's Roles and Responsibilities
  12. Threat Model and Assumptions
  13. Scope: Inference-Level Verification
  14. The Protocol Workflow
  15. Domain Separation and Context Binding
  16. ...and 29 more sections

Key Result

Theorem 1

Let $\mathcal{A}$ be an adversary defined in Algorithm alg:bind-game (see Appendix appendix:security-game) that attacks the binding property of the commitment scheme. If $\mathcal{A}$ can output two distinct tuples $\tau = \{(m_1, s_{sec_1}), (m_2, s_{sec_2})\}$ such that $(m_1, s_{sec_1}) \neq (m_2

Figures (7)

  • Figure 1: City traffic pattern: The perception stack of the Ego vehicle (red car) is not enough to assess the traffic situation fully, since the cyclist is completely occluded by the city buildings. Hence, the Ego vehicle needs perception data from another vehicle (orange car) to fully comprehend the situation and make an informed decision.
  • Figure 2: Sequence diagram of Hermes' Seal.
  • Figure 3: Operational Scenario: The ego vehicle (leading) detects a stop sign on a winding road. It broadcasts a zk-SNARK proof attesting to the stop sign's location and the vehicle's safe stopping distance. The trailing vehicle, whose view is occluded by vegetation, verifies this proof to update its local map and velocity planning.
  • Figure 4: Performance of SnarkJS, RapidSnark and RapidSnark-GPU for proving perception integrity (refer section \ref{['sec:sub:perception-integrity']})
  • Figure 5: Comparison of percentage of time taken by SnarkJS, RapidSnark and RapidSnark-GPU for each of the sub-routines.
  • ...and 2 more figures

Theorems & Definitions (10)

  • Definition 1
  • Definition 2
  • Theorem 1
  • proof
  • Theorem 2
  • proof
  • Definition 3
  • Definition 4
  • Definition 5
  • Definition 6