Collusion-Resistant and Reliable Incentive Mechanism for Federated Learning

Federated learning has won a lot of interest in recent years, due to its capability in collaborative learning and privacy preservation. To ensure the accuracy of outsourced training tasks, task publishers prefer to assign tasks to task workers with a high reputation. However, existing reputation-based incentive mechanisms assume that task publishers are honest, and only task workers would probably behave dishonestly to pollute the federated learning model. Different from existing work, we argue that task publishers would also behave dishonestly, where they would benefit from colluding with task workers to help task workers obtain a high reputation. In this paper, we propose a collusion-resistant and reliable incentive mechanism for federated learning. First, to measure the credibility of both task publishers and task workers, we devise a novel metric named reliability. Second, we devise a new method to compute the task publisher reliability, which is obtained by computing the deviation of reputation scores given by different task publishers, i.e., low reliability is assigned to a task publisher once its deviation is far away from that of other publishers. Third, we propose a bidirectional reputation calculation method based on the basic uncertain information model to compute reputation and reputation reliability for task workers. Furthermore, by integrating an incentive mechanism, our proposed scheme not only effectively defends against collusion attacks but also ensures that only task workers with high reputation, reputation reliability, and the capability to accomplish complex tasks can win a high reward. Finally, we conduct extensive experiments to verify the efficiency and efficacy of our proposed schemes. The results demonstrate that our proposed schemes are not only collusion-resistant but also achieve 6.31% higher test accuracy compared with the state of the art on the MNIST dataset.