Whispers of Data: Unveiling Label Distributions in Federated Learning Through Virtual Client Simulation
This addresses privacy vulnerabilities in federated learning for applications like healthcare or finance, though it is an incremental improvement over existing attacks.
The paper tackles the problem of label distribution inference attacks in federated learning, proposing a novel method that uses virtual client simulation to predict label distributions, achieving superior performance compared to state-of-the-art techniques and remaining effective under differential privacy defenses.
Federated Learning enables collaborative training of a global model across multiple geographically dispersed clients without the need for data sharing. However, it is susceptible to inference attacks, particularly label inference attacks. Existing studies on label distribution inference exhibits sensitive to the specific settings of the victim client and typically underperforms under defensive strategies. In this study, we propose a novel label distribution inference attack that is stable and adaptable to various scenarios. Specifically, we estimate the size of the victim client's dataset and construct several virtual clients tailored to the victim client. We then quantify the temporal generalization of each class label for the virtual clients and utilize the variation in temporal generalization to train an inference model that predicts the label distribution proportions of the victim client. We validate our approach on multiple datasets, including MNIST, Fashion-MNIST, FER2013, and AG-News. The results demonstrate the superiority of our method compared to state-of-the-art techniques. Furthermore, our attack remains effective even under differential privacy defense mechanisms, underscoring its potential for real-world applications.