Privacy-Preserving Incentive Mechanism Design for Federated Cloud-Edge Learning
Tianyu Liu, Boya Di, Peng An, Lingyang Song
Abstract
To avoid the original private data uploading in cloud-edgecomputing, the federated learning (FL) scheme is recently proposed which enhances the privacy preservation. However, the attacks against the uploaded model updates in FL can still cause private data leakage which demotivates the privacy-sensitive participating edge devices. To address this issue, we aim to design a privacy-preserving incentive mechanism for the federated cloud-edge learning (PFCEL) system such that 1) the privacy-sensitive edge devices are motivated to contribute to the local training and model uploading, 2) a trade-off between the private data leakage and the model accuracy is achieved. We first model the data leakage quantitatively from an adversarial perspective, and then formulate the incentive design problem as a three-layer Stackelberg game, where the interaction between the edge servers and edge devices is further formulated as an optimal contract design problem. Extensive theoretical analysis and numerical evaluations demonstrate the effectiveness of our designed mechanism in terms of privacy preservation and system utility.