Privacy-Preserved Incentive Mechanism for Split Learning in Edge Computing System

In the edge computing system, split learning (SL) is an emerging distributed learning approach that allows mobile users (MUs) and edge nodes (ENs) to train the model together without sharing the raw data of the MU. Although MU can preserve its privacy in SL, attacks on the intermediate data at the cut layer for model training can still lead to privacy leakage, which prevents privacy-sensitive MUs from participating in training. Therefore, it is important to implement an effective incentive mechanism to motivate MUs to join SL while preserving their privacy. In this work, from the perspective of maximizing the utility of edge service provider (ESP) while considering the privacy-sensitivity of different MUs, the incentive problem of ESP and MUs is transformed into the utility optimization problem, and an incentive mechanism based on the differential privacy (DP) and contract theory is established to model the interactions between the MUs and EN. The obtained convex optimization problem is obtained through the mathematical derivations, and the optimal contract is presented by solving this problem. The simulation results demonstrate the effectiveness of our proposed privacy preserved incentive mechanism.