Federated learning (FL) has gained significant attention recently as a privacy-enhancing tool to jointly train a machine learning model by multiple participants. The prior work on FL has mostly studied how to protect label privacy during model training. However, model evaluation in FL might also lead to potential leakage of private label information. In this work, we propose an evaluation algorithm that can accurately compute the widely used AUC (area under the curve) metric when using the label differential privacy (DP) in FL. Through extensive experiments, we show our algorithms can compute accurate AUCs compared to the ground truth. The code is available at {\url{https://github.com/bytedance/fedlearner/tree/master/example/privacy/DPAUC}}.
@article{arxiv.2208.12294,
title = {DPAUC: Differentially Private AUC Computation in Federated Learning},
author = {Jiankai Sun and Xin Yang and Yuanshun Yao and Junyuan Xie and Di Wu and Chong Wang},
journal= {arXiv preprint arXiv:2208.12294},
year = {2022}
}
Comments
The Thirty-Seventh AAAI Conference on Artificial Intelligence, AAAI 2023, Track on Safe and Robust AI. arXiv admin note: substantial text overlap with arXiv:2205.12412