Modern vehicular applications have increased computational demands, which in turn have spurred an interest in leveraging vehicles as distributed resources. We propose a novel framework for vehicles to dynamically share their physical resources, such as GPUs and memory, which enables cooperative computation. These physical resource sharing can enhance the overall system efficiency and prevent a single node being overburdened. To ensure secure resource sharing, we employ efficient physical-layer-based key generation to mitigate threats like eavesdropping. We also propose a sharing-participant selection scheme to select the optimal one through evaluation of several factors such as resource availability, and reliability. This approach balances computational efficiency and security among the vehicles participating in sharing resources. Our simulation results showcase the effectiveness of this framework in enhancing computational resource utilization while providing a secure and reliable operation in urban vehicular networks.
Abstract
Published at: 2025 12th International Conference on Future Internet of Things and Cloud (FiCloud)
https://doi.org/10.1109/FiCloud66139.2025.00080
Access Complete Publication
For an in-depth exploration of our findings and methodologies, download here
