Efficient and Trustworthy Block Propagation for Blockchain-enabled Mobile Embodied AI Networks: A Graph Resfusion Approach

• The integration of mobile networks and embodied AI creates Mobile Embodied AI Networks (MEANETs) that require decentralized security solutions like consortium blockchains.
• A cloud model-based trust calculation mechanism effectively considers randomness and fuzziness in evaluating miner reputation, trustworthiness, and risk.
• The proposed graph Resfusion model combines gated graph neural networks and diffusion techniques to efficiently generate optimal block propagation trajectories.
• Simulation results demonstrate that the proposed framework outperforms traditional routing mechanisms in both block propagation efficiency and trustworthiness.
• The graph Resfusion model shows strong adaptability to dynamic network environments and significantly reduces sampling failure rates compared to baseline diffusion models.

· I. INTRODUCTION
· II. RELATED WORK
· III. SYSTEM MODEL
· IV. CLOUD MODEL-BASED TRUST CALCULATION MECHANISM FOR TRUSTWORTHY BLOCK PROPAGATION OPTIMIZATION
· V. GRAPH RESFUSION MODEL-BASED SOLUTION FOR BLOCK PROPAGATION OPTIMIZATION
· VI. SIMULATION RESULTS
· VII. CONCLUSION